Hugging Face's logo

gpantaz
/
vl-pythia-eva-1b

TensorBoard
Safetensors
Model card Files Metrics Community
gpantaz commited on
Commit
420393a
•
1 Parent(s): 4635763

Upload folder using huggingface_hub

Browse files
Files changed (35) hide show
  1. checkpoint-36513/config.json +33 -0
  2. checkpoint-36513/generation_config.json +6 -0
  3. checkpoint-36513/model-00001-of-00002.safetensors +3 -0
  4. checkpoint-36513/model-00002-of-00002.safetensors +3 -0
  5. checkpoint-36513/model.safetensors.index.json +717 -0
  6. checkpoint-36513/optimizer.pt +3 -0
  7. checkpoint-36513/rng_state_0.pth +3 -0
  8. checkpoint-36513/rng_state_1.pth +3 -0
  9. checkpoint-36513/scheduler.pt +3 -0
  10. checkpoint-36513/trainer_state.json +0 -0
  11. checkpoint-36513/training_args.bin +3 -0
  12. checkpoint-40570/config.json +33 -0
  13. checkpoint-40570/generation_config.json +6 -0
  14. checkpoint-40570/model-00001-of-00002.safetensors +3 -0
  15. checkpoint-40570/model-00002-of-00002.safetensors +3 -0
  16. checkpoint-40570/model.safetensors.index.json +717 -0
  17. checkpoint-40570/optimizer.pt +3 -0
  18. checkpoint-40570/rng_state_0.pth +3 -0
  19. checkpoint-40570/rng_state_1.pth +3 -0
  20. checkpoint-40570/scheduler.pt +3 -0
  21. checkpoint-40570/trainer_state.json +0 -0
  22. checkpoint-40570/training_args.bin +3 -0
  23. checkpoint-final/config.json +33 -0
  24. checkpoint-final/generation_config.json +6 -0
  25. checkpoint-final/model-00001-of-00002.safetensors +3 -0
  26. checkpoint-final/model-00002-of-00002.safetensors +3 -0
  27. checkpoint-final/model.safetensors.index.json +717 -0
  28. checkpoint-final/optimizer.pt +3 -0
  29. checkpoint-final/scheduler.pt +3 -0
  30. checkpoint-final/trainer_state.json +0 -0
  31. checkpoint-final/training_args.bin +3 -0
  32. runs/Apr21_22-48-14_gpantaz-mamba-gpu3/events.out.tfevents.1713736112.gpantaz-mamba-gpu3.6464.0 +3 -0
  33. runs/Apr21_23-10-33_gpantaz-mamba-gpu3/events.out.tfevents.1713737453.gpantaz-mamba-gpu3.9017.0 +3 -0
  34. runs/Apr21_23-12-54_gpantaz-mamba-gpu3/events.out.tfevents.1713737592.gpantaz-mamba-gpu3.9956.0 +3 -0
  35. runs/Apr21_23-20-39_gpantaz-mamba-gpu3/events.out.tfevents.1713738057.gpantaz-mamba-gpu3.11832.0 +3 -0
checkpoint-36513/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-1b",
3
+ "architectures": [
4
+ "VLCLIPGPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 0,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 2048,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 8192,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "gpt_neox",
19
+ "num_attention_heads": 8,
20
+ "num_hidden_layers": 16,
21
+ "rope_scaling": null,
22
+ "rotary_emb_base": 10000,
23
+ "rotary_pct": 0.25,
24
+ "select_feature": "patch",
25
+ "select_layer": -2,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.37.1",
29
+ "use_cache": true,
30
+ "use_parallel_residual": true,
31
+ "vision_encoder_name": "timm/eva02_large_patch14_clip_224",
32
+ "vocab_size": 50304
33
+ }
checkpoint-36513/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.37.1"
6
+ }
checkpoint-36513/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33748a77364e4b5ea7781d712fa8ffc945b74c8688f066cbcffbb87fef049def
3
+ size 4997232072
checkpoint-36513/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f53b941057b24d5188398bb6e62e6dfdd8059d1c70a6038d194a0b7bf7d9d507
3
+ size 288429600
checkpoint-36513/model.safetensors.index.json ADDED
@@ -0,0 +1,717 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5285580544
4
+ },
5
+ "weight_map": {
6
+ "embed_out.weight": "model-00001-of-00002.safetensors",
7
+ "gpt_neox.embed_in.weight": "model-00001-of-00002.safetensors",
8
+ "gpt_neox.final_layer_norm.bias": "model-00001-of-00002.safetensors",
9
+ "gpt_neox.final_layer_norm.weight": "model-00001-of-00002.safetensors",
10
+ "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00002.safetensors",
11
+ "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00002.safetensors",
12
+ "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
13
+ "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
14
+ "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
15
+ "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
16
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
17
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
18
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
19
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
20
+ "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
21
+ "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00002.safetensors",
23
+ "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00002.safetensors",
24
+ "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
25
+ "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
26
+ "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
27
+ "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
28
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
29
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
30
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
31
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
32
+ "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
33
+ "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
34
+ "gpt_neox.layers.10.attention.dense.bias": "model-00001-of-00002.safetensors",
35
+ "gpt_neox.layers.10.attention.dense.weight": "model-00001-of-00002.safetensors",
36
+ "gpt_neox.layers.10.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
37
+ "gpt_neox.layers.10.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
38
+ "gpt_neox.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
39
+ "gpt_neox.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
40
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
41
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
42
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
43
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
44
+ "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
45
+ "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
46
+ "gpt_neox.layers.11.attention.dense.bias": "model-00001-of-00002.safetensors",
47
+ "gpt_neox.layers.11.attention.dense.weight": "model-00001-of-00002.safetensors",
48
+ "gpt_neox.layers.11.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
49
+ "gpt_neox.layers.11.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
50
+ "gpt_neox.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
51
+ "gpt_neox.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
52
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
53
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
54
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
55
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
56
+ "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
57
+ "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "gpt_neox.layers.12.attention.dense.bias": "model-00001-of-00002.safetensors",
59
+ "gpt_neox.layers.12.attention.dense.weight": "model-00001-of-00002.safetensors",
60
+ "gpt_neox.layers.12.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
61
+ "gpt_neox.layers.12.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
62
+ "gpt_neox.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
63
+ "gpt_neox.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
64
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
65
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
66
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
67
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
68
+ "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
69
+ "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
70
+ "gpt_neox.layers.13.attention.dense.bias": "model-00001-of-00002.safetensors",
71
+ "gpt_neox.layers.13.attention.dense.weight": "model-00001-of-00002.safetensors",
72
+ "gpt_neox.layers.13.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
73
+ "gpt_neox.layers.13.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
74
+ "gpt_neox.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
75
+ "gpt_neox.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
77
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
78
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
79
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
80
+ "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
81
+ "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
82
+ "gpt_neox.layers.14.attention.dense.bias": "model-00001-of-00002.safetensors",
83
+ "gpt_neox.layers.14.attention.dense.weight": "model-00001-of-00002.safetensors",
84
+ "gpt_neox.layers.14.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
85
+ "gpt_neox.layers.14.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
86
+ "gpt_neox.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
87
+ "gpt_neox.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
88
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
89
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
90
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
91
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
92
+ "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
93
+ "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "gpt_neox.layers.15.attention.dense.bias": "model-00001-of-00002.safetensors",
95
+ "gpt_neox.layers.15.attention.dense.weight": "model-00001-of-00002.safetensors",
96
+ "gpt_neox.layers.15.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
97
+ "gpt_neox.layers.15.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
98
+ "gpt_neox.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
99
+ "gpt_neox.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
100
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
101
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
102
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
103
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
104
+ "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
105
+ "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
106
+ "gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00002.safetensors",
107
+ "gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00002.safetensors",
108
+ "gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
109
+ "gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
110
+ "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
111
+ "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
113
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
114
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
115
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
116
+ "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
117
+ "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
118
+ "gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00002.safetensors",
119
+ "gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00002.safetensors",
120
+ "gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
121
+ "gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
122
+ "gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
123
+ "gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
124
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
125
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
126
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
127
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
128
+ "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
129
+ "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00002.safetensors",
131
+ "gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00002.safetensors",
132
+ "gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
133
+ "gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
134
+ "gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
135
+ "gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
136
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
137
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
138
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
139
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
140
+ "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
141
+ "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
142
+ "gpt_neox.layers.5.attention.dense.bias": "model-00001-of-00002.safetensors",
143
+ "gpt_neox.layers.5.attention.dense.weight": "model-00001-of-00002.safetensors",
144
+ "gpt_neox.layers.5.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
145
+ "gpt_neox.layers.5.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
146
+ "gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
147
+ "gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
148
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
149
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
150
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
151
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
152
+ "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
153
+ "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
154
+ "gpt_neox.layers.6.attention.dense.bias": "model-00001-of-00002.safetensors",
155
+ "gpt_neox.layers.6.attention.dense.weight": "model-00001-of-00002.safetensors",
156
+ "gpt_neox.layers.6.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
157
+ "gpt_neox.layers.6.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
158
+ "gpt_neox.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
159
+ "gpt_neox.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
160
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
161
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
162
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
163
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
164
+ "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
165
+ "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
166
+ "gpt_neox.layers.7.attention.dense.bias": "model-00001-of-00002.safetensors",
167
+ "gpt_neox.layers.7.attention.dense.weight": "model-00001-of-00002.safetensors",
168
+ "gpt_neox.layers.7.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
169
+ "gpt_neox.layers.7.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
170
+ "gpt_neox.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
171
+ "gpt_neox.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
172
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
173
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
174
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
175
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
176
+ "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
177
+ "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
178
+ "gpt_neox.layers.8.attention.dense.bias": "model-00001-of-00002.safetensors",
179
+ "gpt_neox.layers.8.attention.dense.weight": "model-00001-of-00002.safetensors",
180
+ "gpt_neox.layers.8.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
181
+ "gpt_neox.layers.8.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
182
+ "gpt_neox.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
183
+ "gpt_neox.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
184
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
185
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
186
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
187
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
188
+ "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
189
+ "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
190
+ "gpt_neox.layers.9.attention.dense.bias": "model-00001-of-00002.safetensors",
191
+ "gpt_neox.layers.9.attention.dense.weight": "model-00001-of-00002.safetensors",
192
+ "gpt_neox.layers.9.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
193
+ "gpt_neox.layers.9.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
194
+ "gpt_neox.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
195
+ "gpt_neox.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
196
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
197
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
198
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
199
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
200
+ "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
201
+ "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
202
+ "vision_embed_tokens.0.bias": "model-00002-of-00002.safetensors",
203
+ "vision_embed_tokens.0.weight": "model-00002-of-00002.safetensors",
204
+ "vision_embed_tokens.2.bias": "model-00002-of-00002.safetensors",
205
+ "vision_embed_tokens.2.weight": "model-00002-of-00002.safetensors",
206
+ "vision_encoder.blocks.0.attn.k_proj.weight": "model-00001-of-00002.safetensors",
207
+ "vision_encoder.blocks.0.attn.norm.bias": "model-00001-of-00002.safetensors",
208
+ "vision_encoder.blocks.0.attn.norm.weight": "model-00001-of-00002.safetensors",
209
+ "vision_encoder.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
210
+ "vision_encoder.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
211
+ "vision_encoder.blocks.0.attn.q_proj.bias": "model-00001-of-00002.safetensors",
212
+ "vision_encoder.blocks.0.attn.q_proj.weight": "model-00001-of-00002.safetensors",
213
+ "vision_encoder.blocks.0.attn.v_proj.bias": "model-00001-of-00002.safetensors",
214
+ "vision_encoder.blocks.0.attn.v_proj.weight": "model-00001-of-00002.safetensors",
215
+ "vision_encoder.blocks.0.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
216
+ "vision_encoder.blocks.0.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
217
+ "vision_encoder.blocks.0.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
218
+ "vision_encoder.blocks.0.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
219
+ "vision_encoder.blocks.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
220
+ "vision_encoder.blocks.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
221
+ "vision_encoder.blocks.0.mlp.norm.bias": "model-00001-of-00002.safetensors",
222
+ "vision_encoder.blocks.0.mlp.norm.weight": "model-00001-of-00002.safetensors",
223
+ "vision_encoder.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
224
+ "vision_encoder.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
225
+ "vision_encoder.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
226
+ "vision_encoder.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
227
+ "vision_encoder.blocks.1.attn.k_proj.weight": "model-00001-of-00002.safetensors",
228
+ "vision_encoder.blocks.1.attn.norm.bias": "model-00001-of-00002.safetensors",
229
+ "vision_encoder.blocks.1.attn.norm.weight": "model-00001-of-00002.safetensors",
230
+ "vision_encoder.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
231
+ "vision_encoder.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
232
+ "vision_encoder.blocks.1.attn.q_proj.bias": "model-00001-of-00002.safetensors",
233
+ "vision_encoder.blocks.1.attn.q_proj.weight": "model-00001-of-00002.safetensors",
234
+ "vision_encoder.blocks.1.attn.v_proj.bias": "model-00001-of-00002.safetensors",
235
+ "vision_encoder.blocks.1.attn.v_proj.weight": "model-00001-of-00002.safetensors",
236
+ "vision_encoder.blocks.1.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
237
+ "vision_encoder.blocks.1.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
238
+ "vision_encoder.blocks.1.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
239
+ "vision_encoder.blocks.1.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
240
+ "vision_encoder.blocks.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
241
+ "vision_encoder.blocks.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
242
+ "vision_encoder.blocks.1.mlp.norm.bias": "model-00001-of-00002.safetensors",
243
+ "vision_encoder.blocks.1.mlp.norm.weight": "model-00001-of-00002.safetensors",
244
+ "vision_encoder.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
245
+ "vision_encoder.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
246
+ "vision_encoder.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
247
+ "vision_encoder.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
248
+ "vision_encoder.blocks.10.attn.k_proj.weight": "model-00001-of-00002.safetensors",
249
+ "vision_encoder.blocks.10.attn.norm.bias": "model-00001-of-00002.safetensors",
250
+ "vision_encoder.blocks.10.attn.norm.weight": "model-00001-of-00002.safetensors",
251
+ "vision_encoder.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
252
+ "vision_encoder.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
253
+ "vision_encoder.blocks.10.attn.q_proj.bias": "model-00001-of-00002.safetensors",
254
+ "vision_encoder.blocks.10.attn.q_proj.weight": "model-00001-of-00002.safetensors",
255
+ "vision_encoder.blocks.10.attn.v_proj.bias": "model-00001-of-00002.safetensors",
256
+ "vision_encoder.blocks.10.attn.v_proj.weight": "model-00001-of-00002.safetensors",
257
+ "vision_encoder.blocks.10.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
258
+ "vision_encoder.blocks.10.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
259
+ "vision_encoder.blocks.10.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
260
+ "vision_encoder.blocks.10.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
261
+ "vision_encoder.blocks.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
262
+ "vision_encoder.blocks.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
263
+ "vision_encoder.blocks.10.mlp.norm.bias": "model-00001-of-00002.safetensors",
264
+ "vision_encoder.blocks.10.mlp.norm.weight": "model-00001-of-00002.safetensors",
265
+ "vision_encoder.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
266
+ "vision_encoder.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
267
+ "vision_encoder.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
268
+ "vision_encoder.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
269
+ "vision_encoder.blocks.11.attn.k_proj.weight": "model-00001-of-00002.safetensors",
270
+ "vision_encoder.blocks.11.attn.norm.bias": "model-00001-of-00002.safetensors",
271
+ "vision_encoder.blocks.11.attn.norm.weight": "model-00001-of-00002.safetensors",
272
+ "vision_encoder.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
273
+ "vision_encoder.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
274
+ "vision_encoder.blocks.11.attn.q_proj.bias": "model-00001-of-00002.safetensors",
275
+ "vision_encoder.blocks.11.attn.q_proj.weight": "model-00001-of-00002.safetensors",
276
+ "vision_encoder.blocks.11.attn.v_proj.bias": "model-00001-of-00002.safetensors",
277
+ "vision_encoder.blocks.11.attn.v_proj.weight": "model-00001-of-00002.safetensors",
278
+ "vision_encoder.blocks.11.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
279
+ "vision_encoder.blocks.11.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
280
+ "vision_encoder.blocks.11.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
281
+ "vision_encoder.blocks.11.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
282
+ "vision_encoder.blocks.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
283
+ "vision_encoder.blocks.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
284
+ "vision_encoder.blocks.11.mlp.norm.bias": "model-00001-of-00002.safetensors",
285
+ "vision_encoder.blocks.11.mlp.norm.weight": "model-00001-of-00002.safetensors",
286
+ "vision_encoder.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
287
+ "vision_encoder.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
288
+ "vision_encoder.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
289
+ "vision_encoder.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
290
+ "vision_encoder.blocks.12.attn.k_proj.weight": "model-00001-of-00002.safetensors",
291
+ "vision_encoder.blocks.12.attn.norm.bias": "model-00001-of-00002.safetensors",
292
+ "vision_encoder.blocks.12.attn.norm.weight": "model-00001-of-00002.safetensors",
293
+ "vision_encoder.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
294
+ "vision_encoder.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
295
+ "vision_encoder.blocks.12.attn.q_proj.bias": "model-00001-of-00002.safetensors",
296
+ "vision_encoder.blocks.12.attn.q_proj.weight": "model-00001-of-00002.safetensors",
297
+ "vision_encoder.blocks.12.attn.v_proj.bias": "model-00001-of-00002.safetensors",
298
+ "vision_encoder.blocks.12.attn.v_proj.weight": "model-00001-of-00002.safetensors",
299
+ "vision_encoder.blocks.12.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
300
+ "vision_encoder.blocks.12.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
301
+ "vision_encoder.blocks.12.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
302
+ "vision_encoder.blocks.12.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
303
+ "vision_encoder.blocks.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
304
+ "vision_encoder.blocks.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
305
+ "vision_encoder.blocks.12.mlp.norm.bias": "model-00001-of-00002.safetensors",
306
+ "vision_encoder.blocks.12.mlp.norm.weight": "model-00001-of-00002.safetensors",
307
+ "vision_encoder.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
308
+ "vision_encoder.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
309
+ "vision_encoder.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
310
+ "vision_encoder.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
311
+ "vision_encoder.blocks.13.attn.k_proj.weight": "model-00001-of-00002.safetensors",
312
+ "vision_encoder.blocks.13.attn.norm.bias": "model-00001-of-00002.safetensors",
313
+ "vision_encoder.blocks.13.attn.norm.weight": "model-00001-of-00002.safetensors",
314
+ "vision_encoder.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
315
+ "vision_encoder.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
316
+ "vision_encoder.blocks.13.attn.q_proj.bias": "model-00001-of-00002.safetensors",
317
+ "vision_encoder.blocks.13.attn.q_proj.weight": "model-00001-of-00002.safetensors",
318
+ "vision_encoder.blocks.13.attn.v_proj.bias": "model-00001-of-00002.safetensors",
319
+ "vision_encoder.blocks.13.attn.v_proj.weight": "model-00001-of-00002.safetensors",
320
+ "vision_encoder.blocks.13.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
321
+ "vision_encoder.blocks.13.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
322
+ "vision_encoder.blocks.13.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
323
+ "vision_encoder.blocks.13.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
324
+ "vision_encoder.blocks.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
325
+ "vision_encoder.blocks.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
326
+ "vision_encoder.blocks.13.mlp.norm.bias": "model-00001-of-00002.safetensors",
327
+ "vision_encoder.blocks.13.mlp.norm.weight": "model-00001-of-00002.safetensors",
328
+ "vision_encoder.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
329
+ "vision_encoder.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
330
+ "vision_encoder.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
331
+ "vision_encoder.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
332
+ "vision_encoder.blocks.14.attn.k_proj.weight": "model-00001-of-00002.safetensors",
333
+ "vision_encoder.blocks.14.attn.norm.bias": "model-00001-of-00002.safetensors",
334
+ "vision_encoder.blocks.14.attn.norm.weight": "model-00001-of-00002.safetensors",
335
+ "vision_encoder.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
336
+ "vision_encoder.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
337
+ "vision_encoder.blocks.14.attn.q_proj.bias": "model-00001-of-00002.safetensors",
338
+ "vision_encoder.blocks.14.attn.q_proj.weight": "model-00001-of-00002.safetensors",
339
+ "vision_encoder.blocks.14.attn.v_proj.bias": "model-00001-of-00002.safetensors",
340
+ "vision_encoder.blocks.14.attn.v_proj.weight": "model-00001-of-00002.safetensors",
341
+ "vision_encoder.blocks.14.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
342
+ "vision_encoder.blocks.14.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
343
+ "vision_encoder.blocks.14.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
344
+ "vision_encoder.blocks.14.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
345
+ "vision_encoder.blocks.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
346
+ "vision_encoder.blocks.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
347
+ "vision_encoder.blocks.14.mlp.norm.bias": "model-00001-of-00002.safetensors",
348
+ "vision_encoder.blocks.14.mlp.norm.weight": "model-00001-of-00002.safetensors",
349
+ "vision_encoder.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
350
+ "vision_encoder.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
351
+ "vision_encoder.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
352
+ "vision_encoder.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
353
+ "vision_encoder.blocks.15.attn.k_proj.weight": "model-00001-of-00002.safetensors",
354
+ "vision_encoder.blocks.15.attn.norm.bias": "model-00001-of-00002.safetensors",
355
+ "vision_encoder.blocks.15.attn.norm.weight": "model-00001-of-00002.safetensors",
356
+ "vision_encoder.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
357
+ "vision_encoder.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
358
+ "vision_encoder.blocks.15.attn.q_proj.bias": "model-00001-of-00002.safetensors",
359
+ "vision_encoder.blocks.15.attn.q_proj.weight": "model-00001-of-00002.safetensors",
360
+ "vision_encoder.blocks.15.attn.v_proj.bias": "model-00001-of-00002.safetensors",
361
+ "vision_encoder.blocks.15.attn.v_proj.weight": "model-00001-of-00002.safetensors",
362
+ "vision_encoder.blocks.15.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
363
+ "vision_encoder.blocks.15.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
364
+ "vision_encoder.blocks.15.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
365
+ "vision_encoder.blocks.15.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
366
+ "vision_encoder.blocks.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
367
+ "vision_encoder.blocks.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
368
+ "vision_encoder.blocks.15.mlp.norm.bias": "model-00001-of-00002.safetensors",
369
+ "vision_encoder.blocks.15.mlp.norm.weight": "model-00001-of-00002.safetensors",
370
+ "vision_encoder.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
371
+ "vision_encoder.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
372
+ "vision_encoder.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
373
+ "vision_encoder.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
374
+ "vision_encoder.blocks.16.attn.k_proj.weight": "model-00001-of-00002.safetensors",
375
+ "vision_encoder.blocks.16.attn.norm.bias": "model-00001-of-00002.safetensors",
376
+ "vision_encoder.blocks.16.attn.norm.weight": "model-00001-of-00002.safetensors",
377
+ "vision_encoder.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
378
+ "vision_encoder.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
379
+ "vision_encoder.blocks.16.attn.q_proj.bias": "model-00001-of-00002.safetensors",
380
+ "vision_encoder.blocks.16.attn.q_proj.weight": "model-00001-of-00002.safetensors",
381
+ "vision_encoder.blocks.16.attn.v_proj.bias": "model-00001-of-00002.safetensors",
382
+ "vision_encoder.blocks.16.attn.v_proj.weight": "model-00001-of-00002.safetensors",
383
+ "vision_encoder.blocks.16.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
384
+ "vision_encoder.blocks.16.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
385
+ "vision_encoder.blocks.16.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
386
+ "vision_encoder.blocks.16.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
387
+ "vision_encoder.blocks.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
388
+ "vision_encoder.blocks.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
389
+ "vision_encoder.blocks.16.mlp.norm.bias": "model-00001-of-00002.safetensors",
390
+ "vision_encoder.blocks.16.mlp.norm.weight": "model-00001-of-00002.safetensors",
391
+ "vision_encoder.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
392
+ "vision_encoder.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
393
+ "vision_encoder.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
394
+ "vision_encoder.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
395
+ "vision_encoder.blocks.17.attn.k_proj.weight": "model-00001-of-00002.safetensors",
396
+ "vision_encoder.blocks.17.attn.norm.bias": "model-00001-of-00002.safetensors",
397
+ "vision_encoder.blocks.17.attn.norm.weight": "model-00001-of-00002.safetensors",
398
+ "vision_encoder.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
399
+ "vision_encoder.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
400
+ "vision_encoder.blocks.17.attn.q_proj.bias": "model-00001-of-00002.safetensors",
401
+ "vision_encoder.blocks.17.attn.q_proj.weight": "model-00001-of-00002.safetensors",
402
+ "vision_encoder.blocks.17.attn.v_proj.bias": "model-00001-of-00002.safetensors",
403
+ "vision_encoder.blocks.17.attn.v_proj.weight": "model-00001-of-00002.safetensors",
404
+ "vision_encoder.blocks.17.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
405
+ "vision_encoder.blocks.17.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
406
+ "vision_encoder.blocks.17.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
407
+ "vision_encoder.blocks.17.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
408
+ "vision_encoder.blocks.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
409
+ "vision_encoder.blocks.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
410
+ "vision_encoder.blocks.17.mlp.norm.bias": "model-00001-of-00002.safetensors",
411
+ "vision_encoder.blocks.17.mlp.norm.weight": "model-00001-of-00002.safetensors",
412
+ "vision_encoder.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
413
+ "vision_encoder.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
414
+ "vision_encoder.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
415
+ "vision_encoder.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
416
+ "vision_encoder.blocks.18.attn.k_proj.weight": "model-00001-of-00002.safetensors",
417
+ "vision_encoder.blocks.18.attn.norm.bias": "model-00001-of-00002.safetensors",
418
+ "vision_encoder.blocks.18.attn.norm.weight": "model-00001-of-00002.safetensors",
419
+ "vision_encoder.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
420
+ "vision_encoder.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
421
+ "vision_encoder.blocks.18.attn.q_proj.bias": "model-00001-of-00002.safetensors",
422
+ "vision_encoder.blocks.18.attn.q_proj.weight": "model-00001-of-00002.safetensors",
423
+ "vision_encoder.blocks.18.attn.v_proj.bias": "model-00001-of-00002.safetensors",
424
+ "vision_encoder.blocks.18.attn.v_proj.weight": "model-00001-of-00002.safetensors",
425
+ "vision_encoder.blocks.18.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
426
+ "vision_encoder.blocks.18.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
427
+ "vision_encoder.blocks.18.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
428
+ "vision_encoder.blocks.18.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
429
+ "vision_encoder.blocks.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
430
+ "vision_encoder.blocks.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
431
+ "vision_encoder.blocks.18.mlp.norm.bias": "model-00001-of-00002.safetensors",
432
+ "vision_encoder.blocks.18.mlp.norm.weight": "model-00001-of-00002.safetensors",
433
+ "vision_encoder.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
434
+ "vision_encoder.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
435
+ "vision_encoder.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
436
+ "vision_encoder.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
437
+ "vision_encoder.blocks.19.attn.k_proj.weight": "model-00002-of-00002.safetensors",
438
+ "vision_encoder.blocks.19.attn.norm.bias": "model-00002-of-00002.safetensors",
439
+ "vision_encoder.blocks.19.attn.norm.weight": "model-00002-of-00002.safetensors",
440
+ "vision_encoder.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
441
+ "vision_encoder.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
442
+ "vision_encoder.blocks.19.attn.q_proj.bias": "model-00002-of-00002.safetensors",
443
+ "vision_encoder.blocks.19.attn.q_proj.weight": "model-00002-of-00002.safetensors",
444
+ "vision_encoder.blocks.19.attn.v_proj.bias": "model-00002-of-00002.safetensors",
445
+ "vision_encoder.blocks.19.attn.v_proj.weight": "model-00002-of-00002.safetensors",
446
+ "vision_encoder.blocks.19.mlp.fc1_g.bias": "model-00002-of-00002.safetensors",
447
+ "vision_encoder.blocks.19.mlp.fc1_g.weight": "model-00002-of-00002.safetensors",
448
+ "vision_encoder.blocks.19.mlp.fc1_x.bias": "model-00002-of-00002.safetensors",
449
+ "vision_encoder.blocks.19.mlp.fc1_x.weight": "model-00002-of-00002.safetensors",
450
+ "vision_encoder.blocks.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
451
+ "vision_encoder.blocks.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
452
+ "vision_encoder.blocks.19.mlp.norm.bias": "model-00002-of-00002.safetensors",
453
+ "vision_encoder.blocks.19.mlp.norm.weight": "model-00002-of-00002.safetensors",
454
+ "vision_encoder.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
455
+ "vision_encoder.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
456
+ "vision_encoder.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
457
+ "vision_encoder.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
458
+ "vision_encoder.blocks.2.attn.k_proj.weight": "model-00001-of-00002.safetensors",
459
+ "vision_encoder.blocks.2.attn.norm.bias": "model-00001-of-00002.safetensors",
460
+ "vision_encoder.blocks.2.attn.norm.weight": "model-00001-of-00002.safetensors",
461
+ "vision_encoder.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
462
+ "vision_encoder.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
463
+ "vision_encoder.blocks.2.attn.q_proj.bias": "model-00001-of-00002.safetensors",
464
+ "vision_encoder.blocks.2.attn.q_proj.weight": "model-00001-of-00002.safetensors",
465
+ "vision_encoder.blocks.2.attn.v_proj.bias": "model-00001-of-00002.safetensors",
466
+ "vision_encoder.blocks.2.attn.v_proj.weight": "model-00001-of-00002.safetensors",
467
+ "vision_encoder.blocks.2.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
468
+ "vision_encoder.blocks.2.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
469
+ "vision_encoder.blocks.2.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
470
+ "vision_encoder.blocks.2.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
471
+ "vision_encoder.blocks.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
472
+ "vision_encoder.blocks.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
473
+ "vision_encoder.blocks.2.mlp.norm.bias": "model-00001-of-00002.safetensors",
474
+ "vision_encoder.blocks.2.mlp.norm.weight": "model-00001-of-00002.safetensors",
475
+ "vision_encoder.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
476
+ "vision_encoder.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
477
+ "vision_encoder.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
478
+ "vision_encoder.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
479
+ "vision_encoder.blocks.20.attn.k_proj.weight": "model-00002-of-00002.safetensors",
480
+ "vision_encoder.blocks.20.attn.norm.bias": "model-00002-of-00002.safetensors",
481
+ "vision_encoder.blocks.20.attn.norm.weight": "model-00002-of-00002.safetensors",
482
+ "vision_encoder.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
483
+ "vision_encoder.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
484
+ "vision_encoder.blocks.20.attn.q_proj.bias": "model-00002-of-00002.safetensors",
485
+ "vision_encoder.blocks.20.attn.q_proj.weight": "model-00002-of-00002.safetensors",
486
+ "vision_encoder.blocks.20.attn.v_proj.bias": "model-00002-of-00002.safetensors",
487
+ "vision_encoder.blocks.20.attn.v_proj.weight": "model-00002-of-00002.safetensors",
488
+ "vision_encoder.blocks.20.mlp.fc1_g.bias": "model-00002-of-00002.safetensors",
489
+ "vision_encoder.blocks.20.mlp.fc1_g.weight": "model-00002-of-00002.safetensors",
490
+ "vision_encoder.blocks.20.mlp.fc1_x.bias": "model-00002-of-00002.safetensors",
491
+ "vision_encoder.blocks.20.mlp.fc1_x.weight": "model-00002-of-00002.safetensors",
492
+ "vision_encoder.blocks.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
493
+ "vision_encoder.blocks.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
494
+ "vision_encoder.blocks.20.mlp.norm.bias": "model-00002-of-00002.safetensors",
495
+ "vision_encoder.blocks.20.mlp.norm.weight": "model-00002-of-00002.safetensors",
496
+ "vision_encoder.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
497
+ "vision_encoder.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
498
+ "vision_encoder.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
499
+ "vision_encoder.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
500
+ "vision_encoder.blocks.21.attn.k_proj.weight": "model-00002-of-00002.safetensors",
501
+ "vision_encoder.blocks.21.attn.norm.bias": "model-00002-of-00002.safetensors",
502
+ "vision_encoder.blocks.21.attn.norm.weight": "model-00002-of-00002.safetensors",
503
+ "vision_encoder.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
504
+ "vision_encoder.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
505
+ "vision_encoder.blocks.21.attn.q_proj.bias": "model-00002-of-00002.safetensors",
506
+ "vision_encoder.blocks.21.attn.q_proj.weight": "model-00002-of-00002.safetensors",
507
+ "vision_encoder.blocks.21.attn.v_proj.bias": "model-00002-of-00002.safetensors",
508
+ "vision_encoder.blocks.21.attn.v_proj.weight": "model-00002-of-00002.safetensors",
509
+ "vision_encoder.blocks.21.mlp.fc1_g.bias": "model-00002-of-00002.safetensors",
510
+ "vision_encoder.blocks.21.mlp.fc1_g.weight": "model-00002-of-00002.safetensors",
511
+ "vision_encoder.blocks.21.mlp.fc1_x.bias": "model-00002-of-00002.safetensors",
512
+ "vision_encoder.blocks.21.mlp.fc1_x.weight": "model-00002-of-00002.safetensors",
513
+ "vision_encoder.blocks.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
514
+ "vision_encoder.blocks.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
515
+ "vision_encoder.blocks.21.mlp.norm.bias": "model-00002-of-00002.safetensors",
516
+ "vision_encoder.blocks.21.mlp.norm.weight": "model-00002-of-00002.safetensors",
517
+ "vision_encoder.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
518
+ "vision_encoder.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
519
+ "vision_encoder.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
520
+ "vision_encoder.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
521
+ "vision_encoder.blocks.22.attn.k_proj.weight": "model-00002-of-00002.safetensors",
522
+ "vision_encoder.blocks.22.attn.norm.bias": "model-00002-of-00002.safetensors",
523
+ "vision_encoder.blocks.22.attn.norm.weight": "model-00002-of-00002.safetensors",
524
+ "vision_encoder.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
525
+ "vision_encoder.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
526
+ "vision_encoder.blocks.22.attn.q_proj.bias": "model-00002-of-00002.safetensors",
527
+ "vision_encoder.blocks.22.attn.q_proj.weight": "model-00002-of-00002.safetensors",
528
+ "vision_encoder.blocks.22.attn.v_proj.bias": "model-00002-of-00002.safetensors",
529
+ "vision_encoder.blocks.22.attn.v_proj.weight": "model-00002-of-00002.safetensors",
530
+ "vision_encoder.blocks.22.mlp.fc1_g.bias": "model-00002-of-00002.safetensors",
531
+ "vision_encoder.blocks.22.mlp.fc1_g.weight": "model-00002-of-00002.safetensors",
532
+ "vision_encoder.blocks.22.mlp.fc1_x.bias": "model-00002-of-00002.safetensors",
533
+ "vision_encoder.blocks.22.mlp.fc1_x.weight": "model-00002-of-00002.safetensors",
534
+ "vision_encoder.blocks.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
535
+ "vision_encoder.blocks.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
536
+ "vision_encoder.blocks.22.mlp.norm.bias": "model-00002-of-00002.safetensors",
537
+ "vision_encoder.blocks.22.mlp.norm.weight": "model-00002-of-00002.safetensors",
538
+ "vision_encoder.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
539
+ "vision_encoder.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
540
+ "vision_encoder.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
541
+ "vision_encoder.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
542
+ "vision_encoder.blocks.23.attn.k_proj.weight": "model-00002-of-00002.safetensors",
543
+ "vision_encoder.blocks.23.attn.norm.bias": "model-00002-of-00002.safetensors",
544
+ "vision_encoder.blocks.23.attn.norm.weight": "model-00002-of-00002.safetensors",
545
+ "vision_encoder.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
546
+ "vision_encoder.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
547
+ "vision_encoder.blocks.23.attn.q_proj.bias": "model-00002-of-00002.safetensors",
548
+ "vision_encoder.blocks.23.attn.q_proj.weight": "model-00002-of-00002.safetensors",
549
+ "vision_encoder.blocks.23.attn.v_proj.bias": "model-00002-of-00002.safetensors",
550
+ "vision_encoder.blocks.23.attn.v_proj.weight": "model-00002-of-00002.safetensors",
551
+ "vision_encoder.blocks.23.mlp.fc1_g.bias": "model-00002-of-00002.safetensors",
552
+ "vision_encoder.blocks.23.mlp.fc1_g.weight": "model-00002-of-00002.safetensors",
553
+ "vision_encoder.blocks.23.mlp.fc1_x.bias": "model-00002-of-00002.safetensors",
554
+ "vision_encoder.blocks.23.mlp.fc1_x.weight": "model-00002-of-00002.safetensors",
555
+ "vision_encoder.blocks.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
556
+ "vision_encoder.blocks.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
557
+ "vision_encoder.blocks.23.mlp.norm.bias": "model-00002-of-00002.safetensors",
558
+ "vision_encoder.blocks.23.mlp.norm.weight": "model-00002-of-00002.safetensors",
559
+ "vision_encoder.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
560
+ "vision_encoder.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
561
+ "vision_encoder.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
562
+ "vision_encoder.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
563
+ "vision_encoder.blocks.3.attn.k_proj.weight": "model-00001-of-00002.safetensors",
564
+ "vision_encoder.blocks.3.attn.norm.bias": "model-00001-of-00002.safetensors",
565
+ "vision_encoder.blocks.3.attn.norm.weight": "model-00001-of-00002.safetensors",
566
+ "vision_encoder.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
567
+ "vision_encoder.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
568
+ "vision_encoder.blocks.3.attn.q_proj.bias": "model-00001-of-00002.safetensors",
569
+ "vision_encoder.blocks.3.attn.q_proj.weight": "model-00001-of-00002.safetensors",
570
+ "vision_encoder.blocks.3.attn.v_proj.bias": "model-00001-of-00002.safetensors",
571
+ "vision_encoder.blocks.3.attn.v_proj.weight": "model-00001-of-00002.safetensors",
572
+ "vision_encoder.blocks.3.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
573
+ "vision_encoder.blocks.3.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
574
+ "vision_encoder.blocks.3.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
575
+ "vision_encoder.blocks.3.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
576
+ "vision_encoder.blocks.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
577
+ "vision_encoder.blocks.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
578
+ "vision_encoder.blocks.3.mlp.norm.bias": "model-00001-of-00002.safetensors",
579
+ "vision_encoder.blocks.3.mlp.norm.weight": "model-00001-of-00002.safetensors",
580
+ "vision_encoder.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
581
+ "vision_encoder.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
582
+ "vision_encoder.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
583
+ "vision_encoder.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
584
+ "vision_encoder.blocks.4.attn.k_proj.weight": "model-00001-of-00002.safetensors",
585
+ "vision_encoder.blocks.4.attn.norm.bias": "model-00001-of-00002.safetensors",
586
+ "vision_encoder.blocks.4.attn.norm.weight": "model-00001-of-00002.safetensors",
587
+ "vision_encoder.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
588
+ "vision_encoder.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
589
+ "vision_encoder.blocks.4.attn.q_proj.bias": "model-00001-of-00002.safetensors",
590
+ "vision_encoder.blocks.4.attn.q_proj.weight": "model-00001-of-00002.safetensors",
591
+ "vision_encoder.blocks.4.attn.v_proj.bias": "model-00001-of-00002.safetensors",
592
+ "vision_encoder.blocks.4.attn.v_proj.weight": "model-00001-of-00002.safetensors",
593
+ "vision_encoder.blocks.4.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
594
+ "vision_encoder.blocks.4.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
595
+ "vision_encoder.blocks.4.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
596
+ "vision_encoder.blocks.4.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
597
+ "vision_encoder.blocks.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
598
+ "vision_encoder.blocks.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
599
+ "vision_encoder.blocks.4.mlp.norm.bias": "model-00001-of-00002.safetensors",
600
+ "vision_encoder.blocks.4.mlp.norm.weight": "model-00001-of-00002.safetensors",
601
+ "vision_encoder.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
602
+ "vision_encoder.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
603
+ "vision_encoder.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
604
+ "vision_encoder.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
605
+ "vision_encoder.blocks.5.attn.k_proj.weight": "model-00001-of-00002.safetensors",
606
+ "vision_encoder.blocks.5.attn.norm.bias": "model-00001-of-00002.safetensors",
607
+ "vision_encoder.blocks.5.attn.norm.weight": "model-00001-of-00002.safetensors",
608
+ "vision_encoder.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
609
+ "vision_encoder.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
610
+ "vision_encoder.blocks.5.attn.q_proj.bias": "model-00001-of-00002.safetensors",
611
+ "vision_encoder.blocks.5.attn.q_proj.weight": "model-00001-of-00002.safetensors",
612
+ "vision_encoder.blocks.5.attn.v_proj.bias": "model-00001-of-00002.safetensors",
613
+ "vision_encoder.blocks.5.attn.v_proj.weight": "model-00001-of-00002.safetensors",
614
+ "vision_encoder.blocks.5.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
615
+ "vision_encoder.blocks.5.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
616
+ "vision_encoder.blocks.5.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
617
+ "vision_encoder.blocks.5.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
618
+ "vision_encoder.blocks.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
619
+ "vision_encoder.blocks.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
620
+ "vision_encoder.blocks.5.mlp.norm.bias": "model-00001-of-00002.safetensors",
621
+ "vision_encoder.blocks.5.mlp.norm.weight": "model-00001-of-00002.safetensors",
622
+ "vision_encoder.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
623
+ "vision_encoder.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
624
+ "vision_encoder.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
625
+ "vision_encoder.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
626
+ "vision_encoder.blocks.6.attn.k_proj.weight": "model-00001-of-00002.safetensors",
627
+ "vision_encoder.blocks.6.attn.norm.bias": "model-00001-of-00002.safetensors",
628
+ "vision_encoder.blocks.6.attn.norm.weight": "model-00001-of-00002.safetensors",
629
+ "vision_encoder.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
630
+ "vision_encoder.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
631
+ "vision_encoder.blocks.6.attn.q_proj.bias": "model-00001-of-00002.safetensors",
632
+ "vision_encoder.blocks.6.attn.q_proj.weight": "model-00001-of-00002.safetensors",
633
+ "vision_encoder.blocks.6.attn.v_proj.bias": "model-00001-of-00002.safetensors",
634
+ "vision_encoder.blocks.6.attn.v_proj.weight": "model-00001-of-00002.safetensors",
635
+ "vision_encoder.blocks.6.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
636
+ "vision_encoder.blocks.6.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
637
+ "vision_encoder.blocks.6.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
638
+ "vision_encoder.blocks.6.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
639
+ "vision_encoder.blocks.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
640
+ "vision_encoder.blocks.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
641
+ "vision_encoder.blocks.6.mlp.norm.bias": "model-00001-of-00002.safetensors",
642
+ "vision_encoder.blocks.6.mlp.norm.weight": "model-00001-of-00002.safetensors",
643
+ "vision_encoder.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
644
+ "vision_encoder.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
645
+ "vision_encoder.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
646
+ "vision_encoder.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
647
+ "vision_encoder.blocks.7.attn.k_proj.weight": "model-00001-of-00002.safetensors",
648
+ "vision_encoder.blocks.7.attn.norm.bias": "model-00001-of-00002.safetensors",
649
+ "vision_encoder.blocks.7.attn.norm.weight": "model-00001-of-00002.safetensors",
650
+ "vision_encoder.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
651
+ "vision_encoder.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
652
+ "vision_encoder.blocks.7.attn.q_proj.bias": "model-00001-of-00002.safetensors",
653
+ "vision_encoder.blocks.7.attn.q_proj.weight": "model-00001-of-00002.safetensors",
654
+ "vision_encoder.blocks.7.attn.v_proj.bias": "model-00001-of-00002.safetensors",
655
+ "vision_encoder.blocks.7.attn.v_proj.weight": "model-00001-of-00002.safetensors",
656
+ "vision_encoder.blocks.7.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
657
+ "vision_encoder.blocks.7.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
658
+ "vision_encoder.blocks.7.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
659
+ "vision_encoder.blocks.7.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
660
+ "vision_encoder.blocks.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
661
+ "vision_encoder.blocks.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
662
+ "vision_encoder.blocks.7.mlp.norm.bias": "model-00001-of-00002.safetensors",
663
+ "vision_encoder.blocks.7.mlp.norm.weight": "model-00001-of-00002.safetensors",
664
+ "vision_encoder.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
665
+ "vision_encoder.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
666
+ "vision_encoder.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
667
+ "vision_encoder.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
668
+ "vision_encoder.blocks.8.attn.k_proj.weight": "model-00001-of-00002.safetensors",
669
+ "vision_encoder.blocks.8.attn.norm.bias": "model-00001-of-00002.safetensors",
670
+ "vision_encoder.blocks.8.attn.norm.weight": "model-00001-of-00002.safetensors",
671
+ "vision_encoder.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
672
+ "vision_encoder.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
673
+ "vision_encoder.blocks.8.attn.q_proj.bias": "model-00001-of-00002.safetensors",
674
+ "vision_encoder.blocks.8.attn.q_proj.weight": "model-00001-of-00002.safetensors",
675
+ "vision_encoder.blocks.8.attn.v_proj.bias": "model-00001-of-00002.safetensors",
676
+ "vision_encoder.blocks.8.attn.v_proj.weight": "model-00001-of-00002.safetensors",
677
+ "vision_encoder.blocks.8.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
678
+ "vision_encoder.blocks.8.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
679
+ "vision_encoder.blocks.8.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
680
+ "vision_encoder.blocks.8.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
681
+ "vision_encoder.blocks.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
682
+ "vision_encoder.blocks.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
683
+ "vision_encoder.blocks.8.mlp.norm.bias": "model-00001-of-00002.safetensors",
684
+ "vision_encoder.blocks.8.mlp.norm.weight": "model-00001-of-00002.safetensors",
685
+ "vision_encoder.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
686
+ "vision_encoder.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
687
+ "vision_encoder.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
688
+ "vision_encoder.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
689
+ "vision_encoder.blocks.9.attn.k_proj.weight": "model-00001-of-00002.safetensors",
690
+ "vision_encoder.blocks.9.attn.norm.bias": "model-00001-of-00002.safetensors",
691
+ "vision_encoder.blocks.9.attn.norm.weight": "model-00001-of-00002.safetensors",
692
+ "vision_encoder.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
693
+ "vision_encoder.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
694
+ "vision_encoder.blocks.9.attn.q_proj.bias": "model-00001-of-00002.safetensors",
695
+ "vision_encoder.blocks.9.attn.q_proj.weight": "model-00001-of-00002.safetensors",
696
+ "vision_encoder.blocks.9.attn.v_proj.bias": "model-00001-of-00002.safetensors",
697
+ "vision_encoder.blocks.9.attn.v_proj.weight": "model-00001-of-00002.safetensors",
698
+ "vision_encoder.blocks.9.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
699
+ "vision_encoder.blocks.9.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
700
+ "vision_encoder.blocks.9.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
701
+ "vision_encoder.blocks.9.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
702
+ "vision_encoder.blocks.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
703
+ "vision_encoder.blocks.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
704
+ "vision_encoder.blocks.9.mlp.norm.bias": "model-00001-of-00002.safetensors",
705
+ "vision_encoder.blocks.9.mlp.norm.weight": "model-00001-of-00002.safetensors",
706
+ "vision_encoder.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
707
+ "vision_encoder.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
708
+ "vision_encoder.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
709
+ "vision_encoder.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
710
+ "vision_encoder.cls_token": "model-00001-of-00002.safetensors",
711
+ "vision_encoder.norm.bias": "model-00002-of-00002.safetensors",
712
+ "vision_encoder.norm.weight": "model-00002-of-00002.safetensors",
713
+ "vision_encoder.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
714
+ "vision_encoder.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
715
+ "vision_encoder.pos_embed": "model-00001-of-00002.safetensors"
716
+ }
717
+ }
checkpoint-36513/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:004d397c91b70a5e171f9e401d44f1f98c6de8dc4eafb0a3278b1afd74a98395
3
+ size 8144790622
checkpoint-36513/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dceddadb5f65b8a500f4cff9ccece710fd3f542e8476f7f407452082f397725e
3
+ size 14512
checkpoint-36513/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d11f3094b4918b07c7c2bd63273da62eb431adb4f07bb98f70bb671bb7c30b7
3
+ size 14512
checkpoint-36513/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:944e2112ca8150c071da5f4a4969c5d88c4f149803cad42db8a2a60e0c009d7e
3
+ size 1064
checkpoint-36513/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-36513/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08ce939e522ea614879ddb3fd2e44e03c23e1755c44e09d03a427027b54e53d4
3
+ size 4792
checkpoint-40570/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-1b",
3
+ "architectures": [
4
+ "VLCLIPGPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 0,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 2048,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 8192,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "gpt_neox",
19
+ "num_attention_heads": 8,
20
+ "num_hidden_layers": 16,
21
+ "rope_scaling": null,
22
+ "rotary_emb_base": 10000,
23
+ "rotary_pct": 0.25,
24
+ "select_feature": "patch",
25
+ "select_layer": -2,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.37.1",
29
+ "use_cache": true,
30
+ "use_parallel_residual": true,
31
+ "vision_encoder_name": "timm/eva02_large_patch14_clip_224",
32
+ "vocab_size": 50304
33
+ }
checkpoint-40570/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.37.1"
6
+ }
checkpoint-40570/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddac709349cec8e75291c62a58f612fd703cddbc23d6b036c2279f90d2802428
3
+ size 4997232072
checkpoint-40570/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:551d7cbdcb74f8ccfc9bec2b2bc7f376bd552cf0c9ed87d67875810fab23cee5
3
+ size 288429600
checkpoint-40570/model.safetensors.index.json ADDED
@@ -0,0 +1,717 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5285580544
4
+ },
5
+ "weight_map": {
6
+ "embed_out.weight": "model-00001-of-00002.safetensors",
7
+ "gpt_neox.embed_in.weight": "model-00001-of-00002.safetensors",
8
+ "gpt_neox.final_layer_norm.bias": "model-00001-of-00002.safetensors",
9
+ "gpt_neox.final_layer_norm.weight": "model-00001-of-00002.safetensors",
10
+ "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00002.safetensors",
11
+ "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00002.safetensors",
12
+ "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
13
+ "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
14
+ "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
15
+ "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
16
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
17
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
18
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
19
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
20
+ "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
21
+ "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00002.safetensors",
23
+ "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00002.safetensors",
24
+ "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
25
+ "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
26
+ "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
27
+ "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
28
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
29
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
30
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
31
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
32
+ "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
33
+ "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
34
+ "gpt_neox.layers.10.attention.dense.bias": "model-00001-of-00002.safetensors",
35
+ "gpt_neox.layers.10.attention.dense.weight": "model-00001-of-00002.safetensors",
36
+ "gpt_neox.layers.10.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
37
+ "gpt_neox.layers.10.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
38
+ "gpt_neox.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
39
+ "gpt_neox.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
40
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
41
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
42
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
43
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
44
+ "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
45
+ "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
46
+ "gpt_neox.layers.11.attention.dense.bias": "model-00001-of-00002.safetensors",
47
+ "gpt_neox.layers.11.attention.dense.weight": "model-00001-of-00002.safetensors",
48
+ "gpt_neox.layers.11.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
49
+ "gpt_neox.layers.11.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
50
+ "gpt_neox.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
51
+ "gpt_neox.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
52
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
53
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
54
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
55
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
56
+ "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
57
+ "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "gpt_neox.layers.12.attention.dense.bias": "model-00001-of-00002.safetensors",
59
+ "gpt_neox.layers.12.attention.dense.weight": "model-00001-of-00002.safetensors",
60
+ "gpt_neox.layers.12.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
61
+ "gpt_neox.layers.12.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
62
+ "gpt_neox.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
63
+ "gpt_neox.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
64
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
65
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
66
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
67
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
68
+ "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
69
+ "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
70
+ "gpt_neox.layers.13.attention.dense.bias": "model-00001-of-00002.safetensors",
71
+ "gpt_neox.layers.13.attention.dense.weight": "model-00001-of-00002.safetensors",
72
+ "gpt_neox.layers.13.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
73
+ "gpt_neox.layers.13.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
74
+ "gpt_neox.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
75
+ "gpt_neox.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
77
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
78
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
79
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
80
+ "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
81
+ "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
82
+ "gpt_neox.layers.14.attention.dense.bias": "model-00001-of-00002.safetensors",
83
+ "gpt_neox.layers.14.attention.dense.weight": "model-00001-of-00002.safetensors",
84
+ "gpt_neox.layers.14.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
85
+ "gpt_neox.layers.14.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
86
+ "gpt_neox.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
87
+ "gpt_neox.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
88
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
89
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
90
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
91
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
92
+ "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
93
+ "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "gpt_neox.layers.15.attention.dense.bias": "model-00001-of-00002.safetensors",
95
+ "gpt_neox.layers.15.attention.dense.weight": "model-00001-of-00002.safetensors",
96
+ "gpt_neox.layers.15.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
97
+ "gpt_neox.layers.15.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
98
+ "gpt_neox.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
99
+ "gpt_neox.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
100
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
101
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
102
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
103
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
104
+ "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
105
+ "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
106
+ "gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00002.safetensors",
107
+ "gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00002.safetensors",
108
+ "gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
109
+ "gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
110
+ "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
111
+ "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
113
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
114
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
115
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
116
+ "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
117
+ "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
118
+ "gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00002.safetensors",
119
+ "gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00002.safetensors",
120
+ "gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
121
+ "gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
122
+ "gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
123
+ "gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
124
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
125
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
126
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
127
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
128
+ "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
129
+ "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00002.safetensors",
131
+ "gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00002.safetensors",
132
+ "gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
133
+ "gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
134
+ "gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
135
+ "gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
136
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
137
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
138
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
139
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
140
+ "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
141
+ "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
142
+ "gpt_neox.layers.5.attention.dense.bias": "model-00001-of-00002.safetensors",
143
+ "gpt_neox.layers.5.attention.dense.weight": "model-00001-of-00002.safetensors",
144
+ "gpt_neox.layers.5.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
145
+ "gpt_neox.layers.5.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
146
+ "gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
147
+ "gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
148
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
149
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
150
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
151
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
152
+ "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
153
+ "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
154
+ "gpt_neox.layers.6.attention.dense.bias": "model-00001-of-00002.safetensors",
155
+ "gpt_neox.layers.6.attention.dense.weight": "model-00001-of-00002.safetensors",
156
+ "gpt_neox.layers.6.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
157
+ "gpt_neox.layers.6.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
158
+ "gpt_neox.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
159
+ "gpt_neox.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
160
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
161
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
162
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
163
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
164
+ "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
165
+ "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
166
+ "gpt_neox.layers.7.attention.dense.bias": "model-00001-of-00002.safetensors",
167
+ "gpt_neox.layers.7.attention.dense.weight": "model-00001-of-00002.safetensors",
168
+ "gpt_neox.layers.7.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
169
+ "gpt_neox.layers.7.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
170
+ "gpt_neox.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
171
+ "gpt_neox.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
172
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
173
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
174
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
175
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
176
+ "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
177
+ "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
178
+ "gpt_neox.layers.8.attention.dense.bias": "model-00001-of-00002.safetensors",
179
+ "gpt_neox.layers.8.attention.dense.weight": "model-00001-of-00002.safetensors",
180
+ "gpt_neox.layers.8.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
181
+ "gpt_neox.layers.8.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
182
+ "gpt_neox.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
183
+ "gpt_neox.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
184
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
185
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
186
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
187
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
188
+ "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
189
+ "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
190
+ "gpt_neox.layers.9.attention.dense.bias": "model-00001-of-00002.safetensors",
191
+ "gpt_neox.layers.9.attention.dense.weight": "model-00001-of-00002.safetensors",
192
+ "gpt_neox.layers.9.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
193
+ "gpt_neox.layers.9.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
194
+ "gpt_neox.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
195
+ "gpt_neox.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
196
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
197
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
198
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
199
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
200
+ "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
201
+ "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
202
+ "vision_embed_tokens.0.bias": "model-00002-of-00002.safetensors",
203
+ "vision_embed_tokens.0.weight": "model-00002-of-00002.safetensors",
204
+ "vision_embed_tokens.2.bias": "model-00002-of-00002.safetensors",
205
+ "vision_embed_tokens.2.weight": "model-00002-of-00002.safetensors",
206
+ "vision_encoder.blocks.0.attn.k_proj.weight": "model-00001-of-00002.safetensors",
207
+ "vision_encoder.blocks.0.attn.norm.bias": "model-00001-of-00002.safetensors",
208
+ "vision_encoder.blocks.0.attn.norm.weight": "model-00001-of-00002.safetensors",
209
+ "vision_encoder.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
210
+ "vision_encoder.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
211
+ "vision_encoder.blocks.0.attn.q_proj.bias": "model-00001-of-00002.safetensors",
212
+ "vision_encoder.blocks.0.attn.q_proj.weight": "model-00001-of-00002.safetensors",
213
+ "vision_encoder.blocks.0.attn.v_proj.bias": "model-00001-of-00002.safetensors",
214
+ "vision_encoder.blocks.0.attn.v_proj.weight": "model-00001-of-00002.safetensors",
215
+ "vision_encoder.blocks.0.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
216
+ "vision_encoder.blocks.0.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
217
+ "vision_encoder.blocks.0.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
218
+ "vision_encoder.blocks.0.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
219
+ "vision_encoder.blocks.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
220
+ "vision_encoder.blocks.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
221
+ "vision_encoder.blocks.0.mlp.norm.bias": "model-00001-of-00002.safetensors",
222
+ "vision_encoder.blocks.0.mlp.norm.weight": "model-00001-of-00002.safetensors",
223
+ "vision_encoder.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
224
+ "vision_encoder.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
225
+ "vision_encoder.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
226
+ "vision_encoder.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
227
+ "vision_encoder.blocks.1.attn.k_proj.weight": "model-00001-of-00002.safetensors",
228
+ "vision_encoder.blocks.1.attn.norm.bias": "model-00001-of-00002.safetensors",
229
+ "vision_encoder.blocks.1.attn.norm.weight": "model-00001-of-00002.safetensors",
230
+ "vision_encoder.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
231
+ "vision_encoder.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
232
+ "vision_encoder.blocks.1.attn.q_proj.bias": "model-00001-of-00002.safetensors",
233
+ "vision_encoder.blocks.1.attn.q_proj.weight": "model-00001-of-00002.safetensors",
234
+ "vision_encoder.blocks.1.attn.v_proj.bias": "model-00001-of-00002.safetensors",
235
+ "vision_encoder.blocks.1.attn.v_proj.weight": "model-00001-of-00002.safetensors",
236
+ "vision_encoder.blocks.1.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
237
+ "vision_encoder.blocks.1.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
238
+ "vision_encoder.blocks.1.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
239
+ "vision_encoder.blocks.1.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
240
+ "vision_encoder.blocks.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
241
+ "vision_encoder.blocks.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
242
+ "vision_encoder.blocks.1.mlp.norm.bias": "model-00001-of-00002.safetensors",
243
+ "vision_encoder.blocks.1.mlp.norm.weight": "model-00001-of-00002.safetensors",
244
+ "vision_encoder.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
245
+ "vision_encoder.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
246
+ "vision_encoder.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
247
+ "vision_encoder.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
248
+ "vision_encoder.blocks.10.attn.k_proj.weight": "model-00001-of-00002.safetensors",
249
+ "vision_encoder.blocks.10.attn.norm.bias": "model-00001-of-00002.safetensors",
250
+ "vision_encoder.blocks.10.attn.norm.weight": "model-00001-of-00002.safetensors",
251
+ "vision_encoder.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
252
+ "vision_encoder.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
253
+ "vision_encoder.blocks.10.attn.q_proj.bias": "model-00001-of-00002.safetensors",
254
+ "vision_encoder.blocks.10.attn.q_proj.weight": "model-00001-of-00002.safetensors",
255
+ "vision_encoder.blocks.10.attn.v_proj.bias": "model-00001-of-00002.safetensors",
256
+ "vision_encoder.blocks.10.attn.v_proj.weight": "model-00001-of-00002.safetensors",
257
+ "vision_encoder.blocks.10.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
258
+ "vision_encoder.blocks.10.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
259
+ "vision_encoder.blocks.10.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
260
+ "vision_encoder.blocks.10.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
261
+ "vision_encoder.blocks.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
262
+ "vision_encoder.blocks.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
263
+ "vision_encoder.blocks.10.mlp.norm.bias": "model-00001-of-00002.safetensors",
264
+ "vision_encoder.blocks.10.mlp.norm.weight": "model-00001-of-00002.safetensors",
265
+ "vision_encoder.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
266
+ "vision_encoder.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
267
+ "vision_encoder.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
268
+ "vision_encoder.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
269
+ "vision_encoder.blocks.11.attn.k_proj.weight": "model-00001-of-00002.safetensors",
270
+ "vision_encoder.blocks.11.attn.norm.bias": "model-00001-of-00002.safetensors",
271
+ "vision_encoder.blocks.11.attn.norm.weight": "model-00001-of-00002.safetensors",
272
+ "vision_encoder.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
273
+ "vision_encoder.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
274
+ "vision_encoder.blocks.11.attn.q_proj.bias": "model-00001-of-00002.safetensors",
275
+ "vision_encoder.blocks.11.attn.q_proj.weight": "model-00001-of-00002.safetensors",
276
+ "vision_encoder.blocks.11.attn.v_proj.bias": "model-00001-of-00002.safetensors",
277
+ "vision_encoder.blocks.11.attn.v_proj.weight": "model-00001-of-00002.safetensors",
278
+ "vision_encoder.blocks.11.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
279
+ "vision_encoder.blocks.11.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
280
+ "vision_encoder.blocks.11.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
281
+ "vision_encoder.blocks.11.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
282
+ "vision_encoder.blocks.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
283
+ "vision_encoder.blocks.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
284
+ "vision_encoder.blocks.11.mlp.norm.bias": "model-00001-of-00002.safetensors",
285
+ "vision_encoder.blocks.11.mlp.norm.weight": "model-00001-of-00002.safetensors",
286
+ "vision_encoder.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
287
+ "vision_encoder.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
288
+ "vision_encoder.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
289
+ "vision_encoder.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
290
+ "vision_encoder.blocks.12.attn.k_proj.weight": "model-00001-of-00002.safetensors",
291
+ "vision_encoder.blocks.12.attn.norm.bias": "model-00001-of-00002.safetensors",
292
+ "vision_encoder.blocks.12.attn.norm.weight": "model-00001-of-00002.safetensors",
293
+ "vision_encoder.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
294
+ "vision_encoder.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
295
+ "vision_encoder.blocks.12.attn.q_proj.bias": "model-00001-of-00002.safetensors",
296
+ "vision_encoder.blocks.12.attn.q_proj.weight": "model-00001-of-00002.safetensors",
297
+ "vision_encoder.blocks.12.attn.v_proj.bias": "model-00001-of-00002.safetensors",
298
+ "vision_encoder.blocks.12.attn.v_proj.weight": "model-00001-of-00002.safetensors",
299
+ "vision_encoder.blocks.12.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
300
+ "vision_encoder.blocks.12.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
301
+ "vision_encoder.blocks.12.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
302
+ "vision_encoder.blocks.12.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
303
+ "vision_encoder.blocks.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
304
+ "vision_encoder.blocks.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
305
+ "vision_encoder.blocks.12.mlp.norm.bias": "model-00001-of-00002.safetensors",
306
+ "vision_encoder.blocks.12.mlp.norm.weight": "model-00001-of-00002.safetensors",
307
+ "vision_encoder.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
308
+ "vision_encoder.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
309
+ "vision_encoder.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
310
+ "vision_encoder.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
311
+ "vision_encoder.blocks.13.attn.k_proj.weight": "model-00001-of-00002.safetensors",
312
+ "vision_encoder.blocks.13.attn.norm.bias": "model-00001-of-00002.safetensors",
313
+ "vision_encoder.blocks.13.attn.norm.weight": "model-00001-of-00002.safetensors",
314
+ "vision_encoder.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
315
+ "vision_encoder.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
316
+ "vision_encoder.blocks.13.attn.q_proj.bias": "model-00001-of-00002.safetensors",
317
+ "vision_encoder.blocks.13.attn.q_proj.weight": "model-00001-of-00002.safetensors",
318
+ "vision_encoder.blocks.13.attn.v_proj.bias": "model-00001-of-00002.safetensors",
319
+ "vision_encoder.blocks.13.attn.v_proj.weight": "model-00001-of-00002.safetensors",
320
+ "vision_encoder.blocks.13.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
321
+ "vision_encoder.blocks.13.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
322
+ "vision_encoder.blocks.13.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
323
+ "vision_encoder.blocks.13.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
324
+ "vision_encoder.blocks.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
325
+ "vision_encoder.blocks.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
326
+ "vision_encoder.blocks.13.mlp.norm.bias": "model-00001-of-00002.safetensors",
327
+ "vision_encoder.blocks.13.mlp.norm.weight": "model-00001-of-00002.safetensors",
328
+ "vision_encoder.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
329
+ "vision_encoder.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
330
+ "vision_encoder.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
331
+ "vision_encoder.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
332
+ "vision_encoder.blocks.14.attn.k_proj.weight": "model-00001-of-00002.safetensors",
333
+ "vision_encoder.blocks.14.attn.norm.bias": "model-00001-of-00002.safetensors",
334
+ "vision_encoder.blocks.14.attn.norm.weight": "model-00001-of-00002.safetensors",
335
+ "vision_encoder.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
336
+ "vision_encoder.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
337
+ "vision_encoder.blocks.14.attn.q_proj.bias": "model-00001-of-00002.safetensors",
338
+ "vision_encoder.blocks.14.attn.q_proj.weight": "model-00001-of-00002.safetensors",
339
+ "vision_encoder.blocks.14.attn.v_proj.bias": "model-00001-of-00002.safetensors",
340
+ "vision_encoder.blocks.14.attn.v_proj.weight": "model-00001-of-00002.safetensors",
341
+ "vision_encoder.blocks.14.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
342
+ "vision_encoder.blocks.14.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
343
+ "vision_encoder.blocks.14.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
344
+ "vision_encoder.blocks.14.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
345
+ "vision_encoder.blocks.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
346
+ "vision_encoder.blocks.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
347
+ "vision_encoder.blocks.14.mlp.norm.bias": "model-00001-of-00002.safetensors",
348
+ "vision_encoder.blocks.14.mlp.norm.weight": "model-00001-of-00002.safetensors",
349
+ "vision_encoder.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
350
+ "vision_encoder.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
351
+ "vision_encoder.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
352
+ "vision_encoder.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
353
+ "vision_encoder.blocks.15.attn.k_proj.weight": "model-00001-of-00002.safetensors",
354
+ "vision_encoder.blocks.15.attn.norm.bias": "model-00001-of-00002.safetensors",
355
+ "vision_encoder.blocks.15.attn.norm.weight": "model-00001-of-00002.safetensors",
356
+ "vision_encoder.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
357
+ "vision_encoder.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
358
+ "vision_encoder.blocks.15.attn.q_proj.bias": "model-00001-of-00002.safetensors",
359
+ "vision_encoder.blocks.15.attn.q_proj.weight": "model-00001-of-00002.safetensors",
360
+ "vision_encoder.blocks.15.attn.v_proj.bias": "model-00001-of-00002.safetensors",
361
+ "vision_encoder.blocks.15.attn.v_proj.weight": "model-00001-of-00002.safetensors",
362
+ "vision_encoder.blocks.15.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
363
+ "vision_encoder.blocks.15.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
364
+ "vision_encoder.blocks.15.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
365
+ "vision_encoder.blocks.15.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
366
+ "vision_encoder.blocks.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
367
+ "vision_encoder.blocks.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
368
+ "vision_encoder.blocks.15.mlp.norm.bias": "model-00001-of-00002.safetensors",
369
+ "vision_encoder.blocks.15.mlp.norm.weight": "model-00001-of-00002.safetensors",
370
+ "vision_encoder.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
371
+ "vision_encoder.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
372
+ "vision_encoder.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
373
+ "vision_encoder.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
374
+ "vision_encoder.blocks.16.attn.k_proj.weight": "model-00001-of-00002.safetensors",
375
+ "vision_encoder.blocks.16.attn.norm.bias": "model-00001-of-00002.safetensors",
376
+ "vision_encoder.blocks.16.attn.norm.weight": "model-00001-of-00002.safetensors",
377
+ "vision_encoder.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
378
+ "vision_encoder.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
379
+ "vision_encoder.blocks.16.attn.q_proj.bias": "model-00001-of-00002.safetensors",
380
+ "vision_encoder.blocks.16.attn.q_proj.weight": "model-00001-of-00002.safetensors",
381
+ "vision_encoder.blocks.16.attn.v_proj.bias": "model-00001-of-00002.safetensors",
382
+ "vision_encoder.blocks.16.attn.v_proj.weight": "model-00001-of-00002.safetensors",
383
+ "vision_encoder.blocks.16.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
384
+ "vision_encoder.blocks.16.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
385
+ "vision_encoder.blocks.16.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
386
+ "vision_encoder.blocks.16.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
387
+ "vision_encoder.blocks.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
388
+ "vision_encoder.blocks.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
389
+ "vision_encoder.blocks.16.mlp.norm.bias": "model-00001-of-00002.safetensors",
390
+ "vision_encoder.blocks.16.mlp.norm.weight": "model-00001-of-00002.safetensors",
391
+ "vision_encoder.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
392
+ "vision_encoder.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
393
+ "vision_encoder.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
394
+ "vision_encoder.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
395
+ "vision_encoder.blocks.17.attn.k_proj.weight": "model-00001-of-00002.safetensors",
396
+ "vision_encoder.blocks.17.attn.norm.bias": "model-00001-of-00002.safetensors",
397
+ "vision_encoder.blocks.17.attn.norm.weight": "model-00001-of-00002.safetensors",
398
+ "vision_encoder.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
399
+ "vision_encoder.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
400
+ "vision_encoder.blocks.17.attn.q_proj.bias": "model-00001-of-00002.safetensors",
401
+ "vision_encoder.blocks.17.attn.q_proj.weight": "model-00001-of-00002.safetensors",
402
+ "vision_encoder.blocks.17.attn.v_proj.bias": "model-00001-of-00002.safetensors",
403
+ "vision_encoder.blocks.17.attn.v_proj.weight": "model-00001-of-00002.safetensors",
404
+ "vision_encoder.blocks.17.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
405
+ "vision_encoder.blocks.17.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
406
+ "vision_encoder.blocks.17.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
407
+ "vision_encoder.blocks.17.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
408
+ "vision_encoder.blocks.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
409
+ "vision_encoder.blocks.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
410
+ "vision_encoder.blocks.17.mlp.norm.bias": "model-00001-of-00002.safetensors",
411
+ "vision_encoder.blocks.17.mlp.norm.weight": "model-00001-of-00002.safetensors",
412
+ "vision_encoder.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
413
+ "vision_encoder.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
414
+ "vision_encoder.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
415
+ "vision_encoder.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
416
+ "vision_encoder.blocks.18.attn.k_proj.weight": "model-00001-of-00002.safetensors",
417
+ "vision_encoder.blocks.18.attn.norm.bias": "model-00001-of-00002.safetensors",
418
+ "vision_encoder.blocks.18.attn.norm.weight": "model-00001-of-00002.safetensors",
419
+ "vision_encoder.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
420
+ "vision_encoder.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
421
+ "vision_encoder.blocks.18.attn.q_proj.bias": "model-00001-of-00002.safetensors",
422
+ "vision_encoder.blocks.18.attn.q_proj.weight": "model-00001-of-00002.safetensors",
423
+ "vision_encoder.blocks.18.attn.v_proj.bias": "model-00001-of-00002.safetensors",
424
+ "vision_encoder.blocks.18.attn.v_proj.weight": "model-00001-of-00002.safetensors",
425
+ "vision_encoder.blocks.18.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
426
+ "vision_encoder.blocks.18.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
427
+ "vision_encoder.blocks.18.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
428
+ "vision_encoder.blocks.18.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
429
+ "vision_encoder.blocks.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
430
+ "vision_encoder.blocks.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
431
+ "vision_encoder.blocks.18.mlp.norm.bias": "model-00001-of-00002.safetensors",
432
+ "vision_encoder.blocks.18.mlp.norm.weight": "model-00001-of-00002.safetensors",
433
+ "vision_encoder.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
434
+ "vision_encoder.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
435
+ "vision_encoder.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
436
+ "vision_encoder.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
437
+ "vision_encoder.blocks.19.attn.k_proj.weight": "model-00002-of-00002.safetensors",
438
+ "vision_encoder.blocks.19.attn.norm.bias": "model-00002-of-00002.safetensors",
439
+ "vision_encoder.blocks.19.attn.norm.weight": "model-00002-of-00002.safetensors",
440
+ "vision_encoder.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
441
+ "vision_encoder.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
442
+ "vision_encoder.blocks.19.attn.q_proj.bias": "model-00002-of-00002.safetensors",
443
+ "vision_encoder.blocks.19.attn.q_proj.weight": "model-00002-of-00002.safetensors",
444
+ "vision_encoder.blocks.19.attn.v_proj.bias": "model-00002-of-00002.safetensors",
445
+ "vision_encoder.blocks.19.attn.v_proj.weight": "model-00002-of-00002.safetensors",
446
+ "vision_encoder.blocks.19.mlp.fc1_g.bias": "model-00002-of-00002.safetensors",
447
+ "vision_encoder.blocks.19.mlp.fc1_g.weight": "model-00002-of-00002.safetensors",
448
+ "vision_encoder.blocks.19.mlp.fc1_x.bias": "model-00002-of-00002.safetensors",
449
+ "vision_encoder.blocks.19.mlp.fc1_x.weight": "model-00002-of-00002.safetensors",
450
+ "vision_encoder.blocks.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
451
+ "vision_encoder.blocks.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
452
+ "vision_encoder.blocks.19.mlp.norm.bias": "model-00002-of-00002.safetensors",
453
+ "vision_encoder.blocks.19.mlp.norm.weight": "model-00002-of-00002.safetensors",
454
+ "vision_encoder.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
455
+ "vision_encoder.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
456
+ "vision_encoder.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
457
+ "vision_encoder.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
458
+ "vision_encoder.blocks.2.attn.k_proj.weight": "model-00001-of-00002.safetensors",
459
+ "vision_encoder.blocks.2.attn.norm.bias": "model-00001-of-00002.safetensors",
460
+ "vision_encoder.blocks.2.attn.norm.weight": "model-00001-of-00002.safetensors",
461
+ "vision_encoder.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
462
+ "vision_encoder.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
463
+ "vision_encoder.blocks.2.attn.q_proj.bias": "model-00001-of-00002.safetensors",
464
+ "vision_encoder.blocks.2.attn.q_proj.weight": "model-00001-of-00002.safetensors",
465
+ "vision_encoder.blocks.2.attn.v_proj.bias": "model-00001-of-00002.safetensors",
466
+ "vision_encoder.blocks.2.attn.v_proj.weight": "model-00001-of-00002.safetensors",
467
+ "vision_encoder.blocks.2.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
468
+ "vision_encoder.blocks.2.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
469
+ "vision_encoder.blocks.2.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
470
+ "vision_encoder.blocks.2.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
471
+ "vision_encoder.blocks.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
472
+ "vision_encoder.blocks.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
473
+ "vision_encoder.blocks.2.mlp.norm.bias": "model-00001-of-00002.safetensors",
474
+ "vision_encoder.blocks.2.mlp.norm.weight": "model-00001-of-00002.safetensors",
475
+ "vision_encoder.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
476
+ "vision_encoder.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
477
+ "vision_encoder.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
478
+ "vision_encoder.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
479
+ "vision_encoder.blocks.20.attn.k_proj.weight": "model-00002-of-00002.safetensors",
480
+ "vision_encoder.blocks.20.attn.norm.bias": "model-00002-of-00002.safetensors",
481
+ "vision_encoder.blocks.20.attn.norm.weight": "model-00002-of-00002.safetensors",
482
+ "vision_encoder.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
483
+ "vision_encoder.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
484
+ "vision_encoder.blocks.20.attn.q_proj.bias": "model-00002-of-00002.safetensors",
485
+ "vision_encoder.blocks.20.attn.q_proj.weight": "model-00002-of-00002.safetensors",
486
+ "vision_encoder.blocks.20.attn.v_proj.bias": "model-00002-of-00002.safetensors",
487
+ "vision_encoder.blocks.20.attn.v_proj.weight": "model-00002-of-00002.safetensors",
488
+ "vision_encoder.blocks.20.mlp.fc1_g.bias": "model-00002-of-00002.safetensors",
489
+ "vision_encoder.blocks.20.mlp.fc1_g.weight": "model-00002-of-00002.safetensors",
490
+ "vision_encoder.blocks.20.mlp.fc1_x.bias": "model-00002-of-00002.safetensors",
491
+ "vision_encoder.blocks.20.mlp.fc1_x.weight": "model-00002-of-00002.safetensors",
492
+ "vision_encoder.blocks.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
493
+ "vision_encoder.blocks.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
494
+ "vision_encoder.blocks.20.mlp.norm.bias": "model-00002-of-00002.safetensors",
495
+ "vision_encoder.blocks.20.mlp.norm.weight": "model-00002-of-00002.safetensors",
496
+ "vision_encoder.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
497
+ "vision_encoder.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
498
+ "vision_encoder.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
499
+ "vision_encoder.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
500
+ "vision_encoder.blocks.21.attn.k_proj.weight": "model-00002-of-00002.safetensors",
501
+ "vision_encoder.blocks.21.attn.norm.bias": "model-00002-of-00002.safetensors",
502
+ "vision_encoder.blocks.21.attn.norm.weight": "model-00002-of-00002.safetensors",
503
+ "vision_encoder.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
504
+ "vision_encoder.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
505
+ "vision_encoder.blocks.21.attn.q_proj.bias": "model-00002-of-00002.safetensors",
506
+ "vision_encoder.blocks.21.attn.q_proj.weight": "model-00002-of-00002.safetensors",
507
+ "vision_encoder.blocks.21.attn.v_proj.bias": "model-00002-of-00002.safetensors",
508
+ "vision_encoder.blocks.21.attn.v_proj.weight": "model-00002-of-00002.safetensors",
509
+ "vision_encoder.blocks.21.mlp.fc1_g.bias": "model-00002-of-00002.safetensors",
510
+ "vision_encoder.blocks.21.mlp.fc1_g.weight": "model-00002-of-00002.safetensors",
511
+ "vision_encoder.blocks.21.mlp.fc1_x.bias": "model-00002-of-00002.safetensors",
512
+ "vision_encoder.blocks.21.mlp.fc1_x.weight": "model-00002-of-00002.safetensors",
513
+ "vision_encoder.blocks.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
514
+ "vision_encoder.blocks.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
515
+ "vision_encoder.blocks.21.mlp.norm.bias": "model-00002-of-00002.safetensors",
516
+ "vision_encoder.blocks.21.mlp.norm.weight": "model-00002-of-00002.safetensors",
517
+ "vision_encoder.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
518
+ "vision_encoder.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
519
+ "vision_encoder.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
520
+ "vision_encoder.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
521
+ "vision_encoder.blocks.22.attn.k_proj.weight": "model-00002-of-00002.safetensors",
522
+ "vision_encoder.blocks.22.attn.norm.bias": "model-00002-of-00002.safetensors",
523
+ "vision_encoder.blocks.22.attn.norm.weight": "model-00002-of-00002.safetensors",
524
+ "vision_encoder.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
525
+ "vision_encoder.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
526
+ "vision_encoder.blocks.22.attn.q_proj.bias": "model-00002-of-00002.safetensors",
527
+ "vision_encoder.blocks.22.attn.q_proj.weight": "model-00002-of-00002.safetensors",
528
+ "vision_encoder.blocks.22.attn.v_proj.bias": "model-00002-of-00002.safetensors",
529
+ "vision_encoder.blocks.22.attn.v_proj.weight": "model-00002-of-00002.safetensors",
530
+ "vision_encoder.blocks.22.mlp.fc1_g.bias": "model-00002-of-00002.safetensors",
531
+ "vision_encoder.blocks.22.mlp.fc1_g.weight": "model-00002-of-00002.safetensors",
532
+ "vision_encoder.blocks.22.mlp.fc1_x.bias": "model-00002-of-00002.safetensors",
533
+ "vision_encoder.blocks.22.mlp.fc1_x.weight": "model-00002-of-00002.safetensors",
534
+ "vision_encoder.blocks.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
535
+ "vision_encoder.blocks.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
536
+ "vision_encoder.blocks.22.mlp.norm.bias": "model-00002-of-00002.safetensors",
537
+ "vision_encoder.blocks.22.mlp.norm.weight": "model-00002-of-00002.safetensors",
538
+ "vision_encoder.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
539
+ "vision_encoder.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
540
+ "vision_encoder.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
541
+ "vision_encoder.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
542
+ "vision_encoder.blocks.23.attn.k_proj.weight": "model-00002-of-00002.safetensors",
543
+ "vision_encoder.blocks.23.attn.norm.bias": "model-00002-of-00002.safetensors",
544
+ "vision_encoder.blocks.23.attn.norm.weight": "model-00002-of-00002.safetensors",
545
+ "vision_encoder.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
546
+ "vision_encoder.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
547
+ "vision_encoder.blocks.23.attn.q_proj.bias": "model-00002-of-00002.safetensors",
548
+ "vision_encoder.blocks.23.attn.q_proj.weight": "model-00002-of-00002.safetensors",
549
+ "vision_encoder.blocks.23.attn.v_proj.bias": "model-00002-of-00002.safetensors",
550
+ "vision_encoder.blocks.23.attn.v_proj.weight": "model-00002-of-00002.safetensors",
551
+ "vision_encoder.blocks.23.mlp.fc1_g.bias": "model-00002-of-00002.safetensors",
552
+ "vision_encoder.blocks.23.mlp.fc1_g.weight": "model-00002-of-00002.safetensors",
553
+ "vision_encoder.blocks.23.mlp.fc1_x.bias": "model-00002-of-00002.safetensors",
554
+ "vision_encoder.blocks.23.mlp.fc1_x.weight": "model-00002-of-00002.safetensors",
555
+ "vision_encoder.blocks.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
556
+ "vision_encoder.blocks.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
557
+ "vision_encoder.blocks.23.mlp.norm.bias": "model-00002-of-00002.safetensors",
558
+ "vision_encoder.blocks.23.mlp.norm.weight": "model-00002-of-00002.safetensors",
559
+ "vision_encoder.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
560
+ "vision_encoder.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
561
+ "vision_encoder.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
562
+ "vision_encoder.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
563
+ "vision_encoder.blocks.3.attn.k_proj.weight": "model-00001-of-00002.safetensors",
564
+ "vision_encoder.blocks.3.attn.norm.bias": "model-00001-of-00002.safetensors",
565
+ "vision_encoder.blocks.3.attn.norm.weight": "model-00001-of-00002.safetensors",
566
+ "vision_encoder.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
567
+ "vision_encoder.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
568
+ "vision_encoder.blocks.3.attn.q_proj.bias": "model-00001-of-00002.safetensors",
569
+ "vision_encoder.blocks.3.attn.q_proj.weight": "model-00001-of-00002.safetensors",
570
+ "vision_encoder.blocks.3.attn.v_proj.bias": "model-00001-of-00002.safetensors",
571
+ "vision_encoder.blocks.3.attn.v_proj.weight": "model-00001-of-00002.safetensors",
572
+ "vision_encoder.blocks.3.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
573
+ "vision_encoder.blocks.3.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
574
+ "vision_encoder.blocks.3.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
575
+ "vision_encoder.blocks.3.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
576
+ "vision_encoder.blocks.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
577
+ "vision_encoder.blocks.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
578
+ "vision_encoder.blocks.3.mlp.norm.bias": "model-00001-of-00002.safetensors",
579
+ "vision_encoder.blocks.3.mlp.norm.weight": "model-00001-of-00002.safetensors",
580
+ "vision_encoder.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
581
+ "vision_encoder.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
582
+ "vision_encoder.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
583
+ "vision_encoder.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
584
+ "vision_encoder.blocks.4.attn.k_proj.weight": "model-00001-of-00002.safetensors",
585
+ "vision_encoder.blocks.4.attn.norm.bias": "model-00001-of-00002.safetensors",
586
+ "vision_encoder.blocks.4.attn.norm.weight": "model-00001-of-00002.safetensors",
587
+ "vision_encoder.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
588
+ "vision_encoder.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
589
+ "vision_encoder.blocks.4.attn.q_proj.bias": "model-00001-of-00002.safetensors",
590
+ "vision_encoder.blocks.4.attn.q_proj.weight": "model-00001-of-00002.safetensors",
591
+ "vision_encoder.blocks.4.attn.v_proj.bias": "model-00001-of-00002.safetensors",
592
+ "vision_encoder.blocks.4.attn.v_proj.weight": "model-00001-of-00002.safetensors",
593
+ "vision_encoder.blocks.4.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
594
+ "vision_encoder.blocks.4.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
595
+ "vision_encoder.blocks.4.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
596
+ "vision_encoder.blocks.4.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
597
+ "vision_encoder.blocks.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
598
+ "vision_encoder.blocks.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
599
+ "vision_encoder.blocks.4.mlp.norm.bias": "model-00001-of-00002.safetensors",
600
+ "vision_encoder.blocks.4.mlp.norm.weight": "model-00001-of-00002.safetensors",
601
+ "vision_encoder.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
602
+ "vision_encoder.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
603
+ "vision_encoder.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
604
+ "vision_encoder.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
605
+ "vision_encoder.blocks.5.attn.k_proj.weight": "model-00001-of-00002.safetensors",
606
+ "vision_encoder.blocks.5.attn.norm.bias": "model-00001-of-00002.safetensors",
607
+ "vision_encoder.blocks.5.attn.norm.weight": "model-00001-of-00002.safetensors",
608
+ "vision_encoder.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
609
+ "vision_encoder.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
610
+ "vision_encoder.blocks.5.attn.q_proj.bias": "model-00001-of-00002.safetensors",
611
+ "vision_encoder.blocks.5.attn.q_proj.weight": "model-00001-of-00002.safetensors",
612
+ "vision_encoder.blocks.5.attn.v_proj.bias": "model-00001-of-00002.safetensors",
613
+ "vision_encoder.blocks.5.attn.v_proj.weight": "model-00001-of-00002.safetensors",
614
+ "vision_encoder.blocks.5.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
615
+ "vision_encoder.blocks.5.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
616
+ "vision_encoder.blocks.5.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
617
+ "vision_encoder.blocks.5.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
618
+ "vision_encoder.blocks.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
619
+ "vision_encoder.blocks.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
620
+ "vision_encoder.blocks.5.mlp.norm.bias": "model-00001-of-00002.safetensors",
621
+ "vision_encoder.blocks.5.mlp.norm.weight": "model-00001-of-00002.safetensors",
622
+ "vision_encoder.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
623
+ "vision_encoder.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
624
+ "vision_encoder.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
625
+ "vision_encoder.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
626
+ "vision_encoder.blocks.6.attn.k_proj.weight": "model-00001-of-00002.safetensors",
627
+ "vision_encoder.blocks.6.attn.norm.bias": "model-00001-of-00002.safetensors",
628
+ "vision_encoder.blocks.6.attn.norm.weight": "model-00001-of-00002.safetensors",
629
+ "vision_encoder.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
630
+ "vision_encoder.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
631
+ "vision_encoder.blocks.6.attn.q_proj.bias": "model-00001-of-00002.safetensors",
632
+ "vision_encoder.blocks.6.attn.q_proj.weight": "model-00001-of-00002.safetensors",
633
+ "vision_encoder.blocks.6.attn.v_proj.bias": "model-00001-of-00002.safetensors",
634
+ "vision_encoder.blocks.6.attn.v_proj.weight": "model-00001-of-00002.safetensors",
635
+ "vision_encoder.blocks.6.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
636
+ "vision_encoder.blocks.6.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
637
+ "vision_encoder.blocks.6.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
638
+ "vision_encoder.blocks.6.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
639
+ "vision_encoder.blocks.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
640
+ "vision_encoder.blocks.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
641
+ "vision_encoder.blocks.6.mlp.norm.bias": "model-00001-of-00002.safetensors",
642
+ "vision_encoder.blocks.6.mlp.norm.weight": "model-00001-of-00002.safetensors",
643
+ "vision_encoder.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
644
+ "vision_encoder.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
645
+ "vision_encoder.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
646
+ "vision_encoder.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
647
+ "vision_encoder.blocks.7.attn.k_proj.weight": "model-00001-of-00002.safetensors",
648
+ "vision_encoder.blocks.7.attn.norm.bias": "model-00001-of-00002.safetensors",
649
+ "vision_encoder.blocks.7.attn.norm.weight": "model-00001-of-00002.safetensors",
650
+ "vision_encoder.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
651
+ "vision_encoder.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
652
+ "vision_encoder.blocks.7.attn.q_proj.bias": "model-00001-of-00002.safetensors",
653
+ "vision_encoder.blocks.7.attn.q_proj.weight": "model-00001-of-00002.safetensors",
654
+ "vision_encoder.blocks.7.attn.v_proj.bias": "model-00001-of-00002.safetensors",
655
+ "vision_encoder.blocks.7.attn.v_proj.weight": "model-00001-of-00002.safetensors",
656
+ "vision_encoder.blocks.7.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
657
+ "vision_encoder.blocks.7.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
658
+ "vision_encoder.blocks.7.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
659
+ "vision_encoder.blocks.7.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
660
+ "vision_encoder.blocks.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
661
+ "vision_encoder.blocks.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
662
+ "vision_encoder.blocks.7.mlp.norm.bias": "model-00001-of-00002.safetensors",
663
+ "vision_encoder.blocks.7.mlp.norm.weight": "model-00001-of-00002.safetensors",
664
+ "vision_encoder.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
665
+ "vision_encoder.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
666
+ "vision_encoder.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
667
+ "vision_encoder.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
668
+ "vision_encoder.blocks.8.attn.k_proj.weight": "model-00001-of-00002.safetensors",
669
+ "vision_encoder.blocks.8.attn.norm.bias": "model-00001-of-00002.safetensors",
670
+ "vision_encoder.blocks.8.attn.norm.weight": "model-00001-of-00002.safetensors",
671
+ "vision_encoder.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
672
+ "vision_encoder.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
673
+ "vision_encoder.blocks.8.attn.q_proj.bias": "model-00001-of-00002.safetensors",
674
+ "vision_encoder.blocks.8.attn.q_proj.weight": "model-00001-of-00002.safetensors",
675
+ "vision_encoder.blocks.8.attn.v_proj.bias": "model-00001-of-00002.safetensors",
676
+ "vision_encoder.blocks.8.attn.v_proj.weight": "model-00001-of-00002.safetensors",
677
+ "vision_encoder.blocks.8.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
678
+ "vision_encoder.blocks.8.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
679
+ "vision_encoder.blocks.8.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
680
+ "vision_encoder.blocks.8.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
681
+ "vision_encoder.blocks.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
682
+ "vision_encoder.blocks.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
683
+ "vision_encoder.blocks.8.mlp.norm.bias": "model-00001-of-00002.safetensors",
684
+ "vision_encoder.blocks.8.mlp.norm.weight": "model-00001-of-00002.safetensors",
685
+ "vision_encoder.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
686
+ "vision_encoder.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
687
+ "vision_encoder.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
688
+ "vision_encoder.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
689
+ "vision_encoder.blocks.9.attn.k_proj.weight": "model-00001-of-00002.safetensors",
690
+ "vision_encoder.blocks.9.attn.norm.bias": "model-00001-of-00002.safetensors",
691
+ "vision_encoder.blocks.9.attn.norm.weight": "model-00001-of-00002.safetensors",
692
+ "vision_encoder.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
693
+ "vision_encoder.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
694
+ "vision_encoder.blocks.9.attn.q_proj.bias": "model-00001-of-00002.safetensors",
695
+ "vision_encoder.blocks.9.attn.q_proj.weight": "model-00001-of-00002.safetensors",
696
+ "vision_encoder.blocks.9.attn.v_proj.bias": "model-00001-of-00002.safetensors",
697
+ "vision_encoder.blocks.9.attn.v_proj.weight": "model-00001-of-00002.safetensors",
698
+ "vision_encoder.blocks.9.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
699
+ "vision_encoder.blocks.9.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
700
+ "vision_encoder.blocks.9.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
701
+ "vision_encoder.blocks.9.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
702
+ "vision_encoder.blocks.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
703
+ "vision_encoder.blocks.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
704
+ "vision_encoder.blocks.9.mlp.norm.bias": "model-00001-of-00002.safetensors",
705
+ "vision_encoder.blocks.9.mlp.norm.weight": "model-00001-of-00002.safetensors",
706
+ "vision_encoder.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
707
+ "vision_encoder.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
708
+ "vision_encoder.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
709
+ "vision_encoder.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
710
+ "vision_encoder.cls_token": "model-00001-of-00002.safetensors",
711
+ "vision_encoder.norm.bias": "model-00002-of-00002.safetensors",
712
+ "vision_encoder.norm.weight": "model-00002-of-00002.safetensors",
713
+ "vision_encoder.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
714
+ "vision_encoder.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
715
+ "vision_encoder.pos_embed": "model-00001-of-00002.safetensors"
716
+ }
717
+ }
checkpoint-40570/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56f55cc388fdbff8bbfc2ca2fcf113e905357fc706a71a8e113380efaa064364
3
+ size 8144790622
checkpoint-40570/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c97c236549159fd263cc4faedd9bc01864ba290667fbe7a834281987ed4caef8
3
+ size 14512
checkpoint-40570/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e67e2be4a1e3a6205865dc1c101fe504a1d2894f9cc4ff1b2b9473985b684529
3
+ size 14512
checkpoint-40570/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58250fe1dd84fd85660cee4bb7c7aca0811a7569cf941e6f4f9bfca28b2b4f62
3
+ size 1064
checkpoint-40570/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-40570/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08ce939e522ea614879ddb3fd2e44e03c23e1755c44e09d03a427027b54e53d4
3
+ size 4792
checkpoint-final/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-1b",
3
+ "architectures": [
4
+ "VLCLIPGPTNeoXForCausalLM"
5
+ ],
6
+ "attention_bias": true,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "classifier_dropout": 0.1,
10
+ "eos_token_id": 0,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout": 0.0,
13
+ "hidden_size": 2048,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 8192,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 2048,
18
+ "model_type": "gpt_neox",
19
+ "num_attention_heads": 8,
20
+ "num_hidden_layers": 16,
21
+ "rope_scaling": null,
22
+ "rotary_emb_base": 10000,
23
+ "rotary_pct": 0.25,
24
+ "select_feature": "patch",
25
+ "select_layer": -2,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.37.1",
29
+ "use_cache": true,
30
+ "use_parallel_residual": true,
31
+ "vision_encoder_name": "timm/eva02_large_patch14_clip_224",
32
+ "vocab_size": 50304
33
+ }
checkpoint-final/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.37.1"
6
+ }
checkpoint-final/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddac709349cec8e75291c62a58f612fd703cddbc23d6b036c2279f90d2802428
3
+ size 4997232072
checkpoint-final/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:551d7cbdcb74f8ccfc9bec2b2bc7f376bd552cf0c9ed87d67875810fab23cee5
3
+ size 288429600
checkpoint-final/model.safetensors.index.json ADDED
@@ -0,0 +1,717 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 5285580544
4
+ },
5
+ "weight_map": {
6
+ "embed_out.weight": "model-00001-of-00002.safetensors",
7
+ "gpt_neox.embed_in.weight": "model-00001-of-00002.safetensors",
8
+ "gpt_neox.final_layer_norm.bias": "model-00001-of-00002.safetensors",
9
+ "gpt_neox.final_layer_norm.weight": "model-00001-of-00002.safetensors",
10
+ "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00002.safetensors",
11
+ "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00002.safetensors",
12
+ "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
13
+ "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
14
+ "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
15
+ "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
16
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
17
+ "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
18
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
19
+ "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
20
+ "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
21
+ "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00002.safetensors",
23
+ "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00002.safetensors",
24
+ "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
25
+ "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
26
+ "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
27
+ "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
28
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
29
+ "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
30
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
31
+ "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
32
+ "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
33
+ "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
34
+ "gpt_neox.layers.10.attention.dense.bias": "model-00001-of-00002.safetensors",
35
+ "gpt_neox.layers.10.attention.dense.weight": "model-00001-of-00002.safetensors",
36
+ "gpt_neox.layers.10.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
37
+ "gpt_neox.layers.10.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
38
+ "gpt_neox.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
39
+ "gpt_neox.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
40
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
41
+ "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
42
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
43
+ "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
44
+ "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
45
+ "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
46
+ "gpt_neox.layers.11.attention.dense.bias": "model-00001-of-00002.safetensors",
47
+ "gpt_neox.layers.11.attention.dense.weight": "model-00001-of-00002.safetensors",
48
+ "gpt_neox.layers.11.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
49
+ "gpt_neox.layers.11.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
50
+ "gpt_neox.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
51
+ "gpt_neox.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
52
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
53
+ "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
54
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
55
+ "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
56
+ "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
57
+ "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "gpt_neox.layers.12.attention.dense.bias": "model-00001-of-00002.safetensors",
59
+ "gpt_neox.layers.12.attention.dense.weight": "model-00001-of-00002.safetensors",
60
+ "gpt_neox.layers.12.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
61
+ "gpt_neox.layers.12.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
62
+ "gpt_neox.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
63
+ "gpt_neox.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
64
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
65
+ "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
66
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
67
+ "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
68
+ "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
69
+ "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
70
+ "gpt_neox.layers.13.attention.dense.bias": "model-00001-of-00002.safetensors",
71
+ "gpt_neox.layers.13.attention.dense.weight": "model-00001-of-00002.safetensors",
72
+ "gpt_neox.layers.13.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
73
+ "gpt_neox.layers.13.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
74
+ "gpt_neox.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
75
+ "gpt_neox.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
77
+ "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
78
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
79
+ "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
80
+ "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
81
+ "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
82
+ "gpt_neox.layers.14.attention.dense.bias": "model-00001-of-00002.safetensors",
83
+ "gpt_neox.layers.14.attention.dense.weight": "model-00001-of-00002.safetensors",
84
+ "gpt_neox.layers.14.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
85
+ "gpt_neox.layers.14.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
86
+ "gpt_neox.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
87
+ "gpt_neox.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
88
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
89
+ "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
90
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
91
+ "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
92
+ "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
93
+ "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "gpt_neox.layers.15.attention.dense.bias": "model-00001-of-00002.safetensors",
95
+ "gpt_neox.layers.15.attention.dense.weight": "model-00001-of-00002.safetensors",
96
+ "gpt_neox.layers.15.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
97
+ "gpt_neox.layers.15.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
98
+ "gpt_neox.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
99
+ "gpt_neox.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
100
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
101
+ "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
102
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
103
+ "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
104
+ "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
105
+ "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
106
+ "gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00002.safetensors",
107
+ "gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00002.safetensors",
108
+ "gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
109
+ "gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
110
+ "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
111
+ "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
113
+ "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
114
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
115
+ "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
116
+ "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
117
+ "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
118
+ "gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00002.safetensors",
119
+ "gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00002.safetensors",
120
+ "gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
121
+ "gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
122
+ "gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
123
+ "gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
124
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
125
+ "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
126
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
127
+ "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
128
+ "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
129
+ "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00002.safetensors",
131
+ "gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00002.safetensors",
132
+ "gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
133
+ "gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
134
+ "gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
135
+ "gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
136
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
137
+ "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
138
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
139
+ "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
140
+ "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
141
+ "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
142
+ "gpt_neox.layers.5.attention.dense.bias": "model-00001-of-00002.safetensors",
143
+ "gpt_neox.layers.5.attention.dense.weight": "model-00001-of-00002.safetensors",
144
+ "gpt_neox.layers.5.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
145
+ "gpt_neox.layers.5.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
146
+ "gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
147
+ "gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
148
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
149
+ "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
150
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
151
+ "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
152
+ "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
153
+ "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
154
+ "gpt_neox.layers.6.attention.dense.bias": "model-00001-of-00002.safetensors",
155
+ "gpt_neox.layers.6.attention.dense.weight": "model-00001-of-00002.safetensors",
156
+ "gpt_neox.layers.6.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
157
+ "gpt_neox.layers.6.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
158
+ "gpt_neox.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
159
+ "gpt_neox.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
160
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
161
+ "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
162
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
163
+ "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
164
+ "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
165
+ "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
166
+ "gpt_neox.layers.7.attention.dense.bias": "model-00001-of-00002.safetensors",
167
+ "gpt_neox.layers.7.attention.dense.weight": "model-00001-of-00002.safetensors",
168
+ "gpt_neox.layers.7.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
169
+ "gpt_neox.layers.7.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
170
+ "gpt_neox.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
171
+ "gpt_neox.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
172
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
173
+ "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
174
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
175
+ "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
176
+ "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
177
+ "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
178
+ "gpt_neox.layers.8.attention.dense.bias": "model-00001-of-00002.safetensors",
179
+ "gpt_neox.layers.8.attention.dense.weight": "model-00001-of-00002.safetensors",
180
+ "gpt_neox.layers.8.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
181
+ "gpt_neox.layers.8.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
182
+ "gpt_neox.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
183
+ "gpt_neox.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
184
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
185
+ "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
186
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
187
+ "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
188
+ "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
189
+ "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
190
+ "gpt_neox.layers.9.attention.dense.bias": "model-00001-of-00002.safetensors",
191
+ "gpt_neox.layers.9.attention.dense.weight": "model-00001-of-00002.safetensors",
192
+ "gpt_neox.layers.9.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
193
+ "gpt_neox.layers.9.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
194
+ "gpt_neox.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
195
+ "gpt_neox.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
196
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
197
+ "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
198
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
199
+ "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
200
+ "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
201
+ "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
202
+ "vision_embed_tokens.0.bias": "model-00002-of-00002.safetensors",
203
+ "vision_embed_tokens.0.weight": "model-00002-of-00002.safetensors",
204
+ "vision_embed_tokens.2.bias": "model-00002-of-00002.safetensors",
205
+ "vision_embed_tokens.2.weight": "model-00002-of-00002.safetensors",
206
+ "vision_encoder.blocks.0.attn.k_proj.weight": "model-00001-of-00002.safetensors",
207
+ "vision_encoder.blocks.0.attn.norm.bias": "model-00001-of-00002.safetensors",
208
+ "vision_encoder.blocks.0.attn.norm.weight": "model-00001-of-00002.safetensors",
209
+ "vision_encoder.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
210
+ "vision_encoder.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
211
+ "vision_encoder.blocks.0.attn.q_proj.bias": "model-00001-of-00002.safetensors",
212
+ "vision_encoder.blocks.0.attn.q_proj.weight": "model-00001-of-00002.safetensors",
213
+ "vision_encoder.blocks.0.attn.v_proj.bias": "model-00001-of-00002.safetensors",
214
+ "vision_encoder.blocks.0.attn.v_proj.weight": "model-00001-of-00002.safetensors",
215
+ "vision_encoder.blocks.0.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
216
+ "vision_encoder.blocks.0.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
217
+ "vision_encoder.blocks.0.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
218
+ "vision_encoder.blocks.0.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
219
+ "vision_encoder.blocks.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
220
+ "vision_encoder.blocks.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
221
+ "vision_encoder.blocks.0.mlp.norm.bias": "model-00001-of-00002.safetensors",
222
+ "vision_encoder.blocks.0.mlp.norm.weight": "model-00001-of-00002.safetensors",
223
+ "vision_encoder.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
224
+ "vision_encoder.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
225
+ "vision_encoder.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
226
+ "vision_encoder.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
227
+ "vision_encoder.blocks.1.attn.k_proj.weight": "model-00001-of-00002.safetensors",
228
+ "vision_encoder.blocks.1.attn.norm.bias": "model-00001-of-00002.safetensors",
229
+ "vision_encoder.blocks.1.attn.norm.weight": "model-00001-of-00002.safetensors",
230
+ "vision_encoder.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
231
+ "vision_encoder.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
232
+ "vision_encoder.blocks.1.attn.q_proj.bias": "model-00001-of-00002.safetensors",
233
+ "vision_encoder.blocks.1.attn.q_proj.weight": "model-00001-of-00002.safetensors",
234
+ "vision_encoder.blocks.1.attn.v_proj.bias": "model-00001-of-00002.safetensors",
235
+ "vision_encoder.blocks.1.attn.v_proj.weight": "model-00001-of-00002.safetensors",
236
+ "vision_encoder.blocks.1.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
237
+ "vision_encoder.blocks.1.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
238
+ "vision_encoder.blocks.1.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
239
+ "vision_encoder.blocks.1.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
240
+ "vision_encoder.blocks.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
241
+ "vision_encoder.blocks.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
242
+ "vision_encoder.blocks.1.mlp.norm.bias": "model-00001-of-00002.safetensors",
243
+ "vision_encoder.blocks.1.mlp.norm.weight": "model-00001-of-00002.safetensors",
244
+ "vision_encoder.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
245
+ "vision_encoder.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
246
+ "vision_encoder.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
247
+ "vision_encoder.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
248
+ "vision_encoder.blocks.10.attn.k_proj.weight": "model-00001-of-00002.safetensors",
249
+ "vision_encoder.blocks.10.attn.norm.bias": "model-00001-of-00002.safetensors",
250
+ "vision_encoder.blocks.10.attn.norm.weight": "model-00001-of-00002.safetensors",
251
+ "vision_encoder.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
252
+ "vision_encoder.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
253
+ "vision_encoder.blocks.10.attn.q_proj.bias": "model-00001-of-00002.safetensors",
254
+ "vision_encoder.blocks.10.attn.q_proj.weight": "model-00001-of-00002.safetensors",
255
+ "vision_encoder.blocks.10.attn.v_proj.bias": "model-00001-of-00002.safetensors",
256
+ "vision_encoder.blocks.10.attn.v_proj.weight": "model-00001-of-00002.safetensors",
257
+ "vision_encoder.blocks.10.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
258
+ "vision_encoder.blocks.10.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
259
+ "vision_encoder.blocks.10.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
260
+ "vision_encoder.blocks.10.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
261
+ "vision_encoder.blocks.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
262
+ "vision_encoder.blocks.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
263
+ "vision_encoder.blocks.10.mlp.norm.bias": "model-00001-of-00002.safetensors",
264
+ "vision_encoder.blocks.10.mlp.norm.weight": "model-00001-of-00002.safetensors",
265
+ "vision_encoder.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
266
+ "vision_encoder.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
267
+ "vision_encoder.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
268
+ "vision_encoder.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
269
+ "vision_encoder.blocks.11.attn.k_proj.weight": "model-00001-of-00002.safetensors",
270
+ "vision_encoder.blocks.11.attn.norm.bias": "model-00001-of-00002.safetensors",
271
+ "vision_encoder.blocks.11.attn.norm.weight": "model-00001-of-00002.safetensors",
272
+ "vision_encoder.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
273
+ "vision_encoder.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
274
+ "vision_encoder.blocks.11.attn.q_proj.bias": "model-00001-of-00002.safetensors",
275
+ "vision_encoder.blocks.11.attn.q_proj.weight": "model-00001-of-00002.safetensors",
276
+ "vision_encoder.blocks.11.attn.v_proj.bias": "model-00001-of-00002.safetensors",
277
+ "vision_encoder.blocks.11.attn.v_proj.weight": "model-00001-of-00002.safetensors",
278
+ "vision_encoder.blocks.11.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
279
+ "vision_encoder.blocks.11.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
280
+ "vision_encoder.blocks.11.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
281
+ "vision_encoder.blocks.11.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
282
+ "vision_encoder.blocks.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
283
+ "vision_encoder.blocks.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
284
+ "vision_encoder.blocks.11.mlp.norm.bias": "model-00001-of-00002.safetensors",
285
+ "vision_encoder.blocks.11.mlp.norm.weight": "model-00001-of-00002.safetensors",
286
+ "vision_encoder.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
287
+ "vision_encoder.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
288
+ "vision_encoder.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
289
+ "vision_encoder.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
290
+ "vision_encoder.blocks.12.attn.k_proj.weight": "model-00001-of-00002.safetensors",
291
+ "vision_encoder.blocks.12.attn.norm.bias": "model-00001-of-00002.safetensors",
292
+ "vision_encoder.blocks.12.attn.norm.weight": "model-00001-of-00002.safetensors",
293
+ "vision_encoder.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
294
+ "vision_encoder.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
295
+ "vision_encoder.blocks.12.attn.q_proj.bias": "model-00001-of-00002.safetensors",
296
+ "vision_encoder.blocks.12.attn.q_proj.weight": "model-00001-of-00002.safetensors",
297
+ "vision_encoder.blocks.12.attn.v_proj.bias": "model-00001-of-00002.safetensors",
298
+ "vision_encoder.blocks.12.attn.v_proj.weight": "model-00001-of-00002.safetensors",
299
+ "vision_encoder.blocks.12.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
300
+ "vision_encoder.blocks.12.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
301
+ "vision_encoder.blocks.12.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
302
+ "vision_encoder.blocks.12.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
303
+ "vision_encoder.blocks.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
304
+ "vision_encoder.blocks.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
305
+ "vision_encoder.blocks.12.mlp.norm.bias": "model-00001-of-00002.safetensors",
306
+ "vision_encoder.blocks.12.mlp.norm.weight": "model-00001-of-00002.safetensors",
307
+ "vision_encoder.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
308
+ "vision_encoder.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
309
+ "vision_encoder.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
310
+ "vision_encoder.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
311
+ "vision_encoder.blocks.13.attn.k_proj.weight": "model-00001-of-00002.safetensors",
312
+ "vision_encoder.blocks.13.attn.norm.bias": "model-00001-of-00002.safetensors",
313
+ "vision_encoder.blocks.13.attn.norm.weight": "model-00001-of-00002.safetensors",
314
+ "vision_encoder.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
315
+ "vision_encoder.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
316
+ "vision_encoder.blocks.13.attn.q_proj.bias": "model-00001-of-00002.safetensors",
317
+ "vision_encoder.blocks.13.attn.q_proj.weight": "model-00001-of-00002.safetensors",
318
+ "vision_encoder.blocks.13.attn.v_proj.bias": "model-00001-of-00002.safetensors",
319
+ "vision_encoder.blocks.13.attn.v_proj.weight": "model-00001-of-00002.safetensors",
320
+ "vision_encoder.blocks.13.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
321
+ "vision_encoder.blocks.13.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
322
+ "vision_encoder.blocks.13.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
323
+ "vision_encoder.blocks.13.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
324
+ "vision_encoder.blocks.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
325
+ "vision_encoder.blocks.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
326
+ "vision_encoder.blocks.13.mlp.norm.bias": "model-00001-of-00002.safetensors",
327
+ "vision_encoder.blocks.13.mlp.norm.weight": "model-00001-of-00002.safetensors",
328
+ "vision_encoder.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
329
+ "vision_encoder.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
330
+ "vision_encoder.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
331
+ "vision_encoder.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
332
+ "vision_encoder.blocks.14.attn.k_proj.weight": "model-00001-of-00002.safetensors",
333
+ "vision_encoder.blocks.14.attn.norm.bias": "model-00001-of-00002.safetensors",
334
+ "vision_encoder.blocks.14.attn.norm.weight": "model-00001-of-00002.safetensors",
335
+ "vision_encoder.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
336
+ "vision_encoder.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
337
+ "vision_encoder.blocks.14.attn.q_proj.bias": "model-00001-of-00002.safetensors",
338
+ "vision_encoder.blocks.14.attn.q_proj.weight": "model-00001-of-00002.safetensors",
339
+ "vision_encoder.blocks.14.attn.v_proj.bias": "model-00001-of-00002.safetensors",
340
+ "vision_encoder.blocks.14.attn.v_proj.weight": "model-00001-of-00002.safetensors",
341
+ "vision_encoder.blocks.14.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
342
+ "vision_encoder.blocks.14.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
343
+ "vision_encoder.blocks.14.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
344
+ "vision_encoder.blocks.14.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
345
+ "vision_encoder.blocks.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
346
+ "vision_encoder.blocks.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
347
+ "vision_encoder.blocks.14.mlp.norm.bias": "model-00001-of-00002.safetensors",
348
+ "vision_encoder.blocks.14.mlp.norm.weight": "model-00001-of-00002.safetensors",
349
+ "vision_encoder.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
350
+ "vision_encoder.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
351
+ "vision_encoder.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
352
+ "vision_encoder.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
353
+ "vision_encoder.blocks.15.attn.k_proj.weight": "model-00001-of-00002.safetensors",
354
+ "vision_encoder.blocks.15.attn.norm.bias": "model-00001-of-00002.safetensors",
355
+ "vision_encoder.blocks.15.attn.norm.weight": "model-00001-of-00002.safetensors",
356
+ "vision_encoder.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
357
+ "vision_encoder.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
358
+ "vision_encoder.blocks.15.attn.q_proj.bias": "model-00001-of-00002.safetensors",
359
+ "vision_encoder.blocks.15.attn.q_proj.weight": "model-00001-of-00002.safetensors",
360
+ "vision_encoder.blocks.15.attn.v_proj.bias": "model-00001-of-00002.safetensors",
361
+ "vision_encoder.blocks.15.attn.v_proj.weight": "model-00001-of-00002.safetensors",
362
+ "vision_encoder.blocks.15.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
363
+ "vision_encoder.blocks.15.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
364
+ "vision_encoder.blocks.15.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
365
+ "vision_encoder.blocks.15.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
366
+ "vision_encoder.blocks.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
367
+ "vision_encoder.blocks.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
368
+ "vision_encoder.blocks.15.mlp.norm.bias": "model-00001-of-00002.safetensors",
369
+ "vision_encoder.blocks.15.mlp.norm.weight": "model-00001-of-00002.safetensors",
370
+ "vision_encoder.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
371
+ "vision_encoder.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
372
+ "vision_encoder.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
373
+ "vision_encoder.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
374
+ "vision_encoder.blocks.16.attn.k_proj.weight": "model-00001-of-00002.safetensors",
375
+ "vision_encoder.blocks.16.attn.norm.bias": "model-00001-of-00002.safetensors",
376
+ "vision_encoder.blocks.16.attn.norm.weight": "model-00001-of-00002.safetensors",
377
+ "vision_encoder.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
378
+ "vision_encoder.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
379
+ "vision_encoder.blocks.16.attn.q_proj.bias": "model-00001-of-00002.safetensors",
380
+ "vision_encoder.blocks.16.attn.q_proj.weight": "model-00001-of-00002.safetensors",
381
+ "vision_encoder.blocks.16.attn.v_proj.bias": "model-00001-of-00002.safetensors",
382
+ "vision_encoder.blocks.16.attn.v_proj.weight": "model-00001-of-00002.safetensors",
383
+ "vision_encoder.blocks.16.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
384
+ "vision_encoder.blocks.16.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
385
+ "vision_encoder.blocks.16.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
386
+ "vision_encoder.blocks.16.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
387
+ "vision_encoder.blocks.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
388
+ "vision_encoder.blocks.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
389
+ "vision_encoder.blocks.16.mlp.norm.bias": "model-00001-of-00002.safetensors",
390
+ "vision_encoder.blocks.16.mlp.norm.weight": "model-00001-of-00002.safetensors",
391
+ "vision_encoder.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
392
+ "vision_encoder.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
393
+ "vision_encoder.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
394
+ "vision_encoder.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
395
+ "vision_encoder.blocks.17.attn.k_proj.weight": "model-00001-of-00002.safetensors",
396
+ "vision_encoder.blocks.17.attn.norm.bias": "model-00001-of-00002.safetensors",
397
+ "vision_encoder.blocks.17.attn.norm.weight": "model-00001-of-00002.safetensors",
398
+ "vision_encoder.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
399
+ "vision_encoder.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
400
+ "vision_encoder.blocks.17.attn.q_proj.bias": "model-00001-of-00002.safetensors",
401
+ "vision_encoder.blocks.17.attn.q_proj.weight": "model-00001-of-00002.safetensors",
402
+ "vision_encoder.blocks.17.attn.v_proj.bias": "model-00001-of-00002.safetensors",
403
+ "vision_encoder.blocks.17.attn.v_proj.weight": "model-00001-of-00002.safetensors",
404
+ "vision_encoder.blocks.17.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
405
+ "vision_encoder.blocks.17.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
406
+ "vision_encoder.blocks.17.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
407
+ "vision_encoder.blocks.17.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
408
+ "vision_encoder.blocks.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
409
+ "vision_encoder.blocks.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
410
+ "vision_encoder.blocks.17.mlp.norm.bias": "model-00001-of-00002.safetensors",
411
+ "vision_encoder.blocks.17.mlp.norm.weight": "model-00001-of-00002.safetensors",
412
+ "vision_encoder.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
413
+ "vision_encoder.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
414
+ "vision_encoder.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
415
+ "vision_encoder.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
416
+ "vision_encoder.blocks.18.attn.k_proj.weight": "model-00001-of-00002.safetensors",
417
+ "vision_encoder.blocks.18.attn.norm.bias": "model-00001-of-00002.safetensors",
418
+ "vision_encoder.blocks.18.attn.norm.weight": "model-00001-of-00002.safetensors",
419
+ "vision_encoder.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
420
+ "vision_encoder.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
421
+ "vision_encoder.blocks.18.attn.q_proj.bias": "model-00001-of-00002.safetensors",
422
+ "vision_encoder.blocks.18.attn.q_proj.weight": "model-00001-of-00002.safetensors",
423
+ "vision_encoder.blocks.18.attn.v_proj.bias": "model-00001-of-00002.safetensors",
424
+ "vision_encoder.blocks.18.attn.v_proj.weight": "model-00001-of-00002.safetensors",
425
+ "vision_encoder.blocks.18.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
426
+ "vision_encoder.blocks.18.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
427
+ "vision_encoder.blocks.18.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
428
+ "vision_encoder.blocks.18.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
429
+ "vision_encoder.blocks.18.mlp.fc2.bias": "model-00002-of-00002.safetensors",
430
+ "vision_encoder.blocks.18.mlp.fc2.weight": "model-00002-of-00002.safetensors",
431
+ "vision_encoder.blocks.18.mlp.norm.bias": "model-00001-of-00002.safetensors",
432
+ "vision_encoder.blocks.18.mlp.norm.weight": "model-00001-of-00002.safetensors",
433
+ "vision_encoder.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
434
+ "vision_encoder.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
435
+ "vision_encoder.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
436
+ "vision_encoder.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
437
+ "vision_encoder.blocks.19.attn.k_proj.weight": "model-00002-of-00002.safetensors",
438
+ "vision_encoder.blocks.19.attn.norm.bias": "model-00002-of-00002.safetensors",
439
+ "vision_encoder.blocks.19.attn.norm.weight": "model-00002-of-00002.safetensors",
440
+ "vision_encoder.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
441
+ "vision_encoder.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
442
+ "vision_encoder.blocks.19.attn.q_proj.bias": "model-00002-of-00002.safetensors",
443
+ "vision_encoder.blocks.19.attn.q_proj.weight": "model-00002-of-00002.safetensors",
444
+ "vision_encoder.blocks.19.attn.v_proj.bias": "model-00002-of-00002.safetensors",
445
+ "vision_encoder.blocks.19.attn.v_proj.weight": "model-00002-of-00002.safetensors",
446
+ "vision_encoder.blocks.19.mlp.fc1_g.bias": "model-00002-of-00002.safetensors",
447
+ "vision_encoder.blocks.19.mlp.fc1_g.weight": "model-00002-of-00002.safetensors",
448
+ "vision_encoder.blocks.19.mlp.fc1_x.bias": "model-00002-of-00002.safetensors",
449
+ "vision_encoder.blocks.19.mlp.fc1_x.weight": "model-00002-of-00002.safetensors",
450
+ "vision_encoder.blocks.19.mlp.fc2.bias": "model-00002-of-00002.safetensors",
451
+ "vision_encoder.blocks.19.mlp.fc2.weight": "model-00002-of-00002.safetensors",
452
+ "vision_encoder.blocks.19.mlp.norm.bias": "model-00002-of-00002.safetensors",
453
+ "vision_encoder.blocks.19.mlp.norm.weight": "model-00002-of-00002.safetensors",
454
+ "vision_encoder.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
455
+ "vision_encoder.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
456
+ "vision_encoder.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
457
+ "vision_encoder.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
458
+ "vision_encoder.blocks.2.attn.k_proj.weight": "model-00001-of-00002.safetensors",
459
+ "vision_encoder.blocks.2.attn.norm.bias": "model-00001-of-00002.safetensors",
460
+ "vision_encoder.blocks.2.attn.norm.weight": "model-00001-of-00002.safetensors",
461
+ "vision_encoder.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
462
+ "vision_encoder.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
463
+ "vision_encoder.blocks.2.attn.q_proj.bias": "model-00001-of-00002.safetensors",
464
+ "vision_encoder.blocks.2.attn.q_proj.weight": "model-00001-of-00002.safetensors",
465
+ "vision_encoder.blocks.2.attn.v_proj.bias": "model-00001-of-00002.safetensors",
466
+ "vision_encoder.blocks.2.attn.v_proj.weight": "model-00001-of-00002.safetensors",
467
+ "vision_encoder.blocks.2.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
468
+ "vision_encoder.blocks.2.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
469
+ "vision_encoder.blocks.2.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
470
+ "vision_encoder.blocks.2.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
471
+ "vision_encoder.blocks.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
472
+ "vision_encoder.blocks.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
473
+ "vision_encoder.blocks.2.mlp.norm.bias": "model-00001-of-00002.safetensors",
474
+ "vision_encoder.blocks.2.mlp.norm.weight": "model-00001-of-00002.safetensors",
475
+ "vision_encoder.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
476
+ "vision_encoder.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
477
+ "vision_encoder.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
478
+ "vision_encoder.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
479
+ "vision_encoder.blocks.20.attn.k_proj.weight": "model-00002-of-00002.safetensors",
480
+ "vision_encoder.blocks.20.attn.norm.bias": "model-00002-of-00002.safetensors",
481
+ "vision_encoder.blocks.20.attn.norm.weight": "model-00002-of-00002.safetensors",
482
+ "vision_encoder.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
483
+ "vision_encoder.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
484
+ "vision_encoder.blocks.20.attn.q_proj.bias": "model-00002-of-00002.safetensors",
485
+ "vision_encoder.blocks.20.attn.q_proj.weight": "model-00002-of-00002.safetensors",
486
+ "vision_encoder.blocks.20.attn.v_proj.bias": "model-00002-of-00002.safetensors",
487
+ "vision_encoder.blocks.20.attn.v_proj.weight": "model-00002-of-00002.safetensors",
488
+ "vision_encoder.blocks.20.mlp.fc1_g.bias": "model-00002-of-00002.safetensors",
489
+ "vision_encoder.blocks.20.mlp.fc1_g.weight": "model-00002-of-00002.safetensors",
490
+ "vision_encoder.blocks.20.mlp.fc1_x.bias": "model-00002-of-00002.safetensors",
491
+ "vision_encoder.blocks.20.mlp.fc1_x.weight": "model-00002-of-00002.safetensors",
492
+ "vision_encoder.blocks.20.mlp.fc2.bias": "model-00002-of-00002.safetensors",
493
+ "vision_encoder.blocks.20.mlp.fc2.weight": "model-00002-of-00002.safetensors",
494
+ "vision_encoder.blocks.20.mlp.norm.bias": "model-00002-of-00002.safetensors",
495
+ "vision_encoder.blocks.20.mlp.norm.weight": "model-00002-of-00002.safetensors",
496
+ "vision_encoder.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
497
+ "vision_encoder.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
498
+ "vision_encoder.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
499
+ "vision_encoder.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
500
+ "vision_encoder.blocks.21.attn.k_proj.weight": "model-00002-of-00002.safetensors",
501
+ "vision_encoder.blocks.21.attn.norm.bias": "model-00002-of-00002.safetensors",
502
+ "vision_encoder.blocks.21.attn.norm.weight": "model-00002-of-00002.safetensors",
503
+ "vision_encoder.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
504
+ "vision_encoder.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
505
+ "vision_encoder.blocks.21.attn.q_proj.bias": "model-00002-of-00002.safetensors",
506
+ "vision_encoder.blocks.21.attn.q_proj.weight": "model-00002-of-00002.safetensors",
507
+ "vision_encoder.blocks.21.attn.v_proj.bias": "model-00002-of-00002.safetensors",
508
+ "vision_encoder.blocks.21.attn.v_proj.weight": "model-00002-of-00002.safetensors",
509
+ "vision_encoder.blocks.21.mlp.fc1_g.bias": "model-00002-of-00002.safetensors",
510
+ "vision_encoder.blocks.21.mlp.fc1_g.weight": "model-00002-of-00002.safetensors",
511
+ "vision_encoder.blocks.21.mlp.fc1_x.bias": "model-00002-of-00002.safetensors",
512
+ "vision_encoder.blocks.21.mlp.fc1_x.weight": "model-00002-of-00002.safetensors",
513
+ "vision_encoder.blocks.21.mlp.fc2.bias": "model-00002-of-00002.safetensors",
514
+ "vision_encoder.blocks.21.mlp.fc2.weight": "model-00002-of-00002.safetensors",
515
+ "vision_encoder.blocks.21.mlp.norm.bias": "model-00002-of-00002.safetensors",
516
+ "vision_encoder.blocks.21.mlp.norm.weight": "model-00002-of-00002.safetensors",
517
+ "vision_encoder.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
518
+ "vision_encoder.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
519
+ "vision_encoder.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
520
+ "vision_encoder.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
521
+ "vision_encoder.blocks.22.attn.k_proj.weight": "model-00002-of-00002.safetensors",
522
+ "vision_encoder.blocks.22.attn.norm.bias": "model-00002-of-00002.safetensors",
523
+ "vision_encoder.blocks.22.attn.norm.weight": "model-00002-of-00002.safetensors",
524
+ "vision_encoder.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
525
+ "vision_encoder.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
526
+ "vision_encoder.blocks.22.attn.q_proj.bias": "model-00002-of-00002.safetensors",
527
+ "vision_encoder.blocks.22.attn.q_proj.weight": "model-00002-of-00002.safetensors",
528
+ "vision_encoder.blocks.22.attn.v_proj.bias": "model-00002-of-00002.safetensors",
529
+ "vision_encoder.blocks.22.attn.v_proj.weight": "model-00002-of-00002.safetensors",
530
+ "vision_encoder.blocks.22.mlp.fc1_g.bias": "model-00002-of-00002.safetensors",
531
+ "vision_encoder.blocks.22.mlp.fc1_g.weight": "model-00002-of-00002.safetensors",
532
+ "vision_encoder.blocks.22.mlp.fc1_x.bias": "model-00002-of-00002.safetensors",
533
+ "vision_encoder.blocks.22.mlp.fc1_x.weight": "model-00002-of-00002.safetensors",
534
+ "vision_encoder.blocks.22.mlp.fc2.bias": "model-00002-of-00002.safetensors",
535
+ "vision_encoder.blocks.22.mlp.fc2.weight": "model-00002-of-00002.safetensors",
536
+ "vision_encoder.blocks.22.mlp.norm.bias": "model-00002-of-00002.safetensors",
537
+ "vision_encoder.blocks.22.mlp.norm.weight": "model-00002-of-00002.safetensors",
538
+ "vision_encoder.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
539
+ "vision_encoder.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
540
+ "vision_encoder.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
541
+ "vision_encoder.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
542
+ "vision_encoder.blocks.23.attn.k_proj.weight": "model-00002-of-00002.safetensors",
543
+ "vision_encoder.blocks.23.attn.norm.bias": "model-00002-of-00002.safetensors",
544
+ "vision_encoder.blocks.23.attn.norm.weight": "model-00002-of-00002.safetensors",
545
+ "vision_encoder.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
546
+ "vision_encoder.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
547
+ "vision_encoder.blocks.23.attn.q_proj.bias": "model-00002-of-00002.safetensors",
548
+ "vision_encoder.blocks.23.attn.q_proj.weight": "model-00002-of-00002.safetensors",
549
+ "vision_encoder.blocks.23.attn.v_proj.bias": "model-00002-of-00002.safetensors",
550
+ "vision_encoder.blocks.23.attn.v_proj.weight": "model-00002-of-00002.safetensors",
551
+ "vision_encoder.blocks.23.mlp.fc1_g.bias": "model-00002-of-00002.safetensors",
552
+ "vision_encoder.blocks.23.mlp.fc1_g.weight": "model-00002-of-00002.safetensors",
553
+ "vision_encoder.blocks.23.mlp.fc1_x.bias": "model-00002-of-00002.safetensors",
554
+ "vision_encoder.blocks.23.mlp.fc1_x.weight": "model-00002-of-00002.safetensors",
555
+ "vision_encoder.blocks.23.mlp.fc2.bias": "model-00002-of-00002.safetensors",
556
+ "vision_encoder.blocks.23.mlp.fc2.weight": "model-00002-of-00002.safetensors",
557
+ "vision_encoder.blocks.23.mlp.norm.bias": "model-00002-of-00002.safetensors",
558
+ "vision_encoder.blocks.23.mlp.norm.weight": "model-00002-of-00002.safetensors",
559
+ "vision_encoder.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
560
+ "vision_encoder.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
561
+ "vision_encoder.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
562
+ "vision_encoder.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
563
+ "vision_encoder.blocks.3.attn.k_proj.weight": "model-00001-of-00002.safetensors",
564
+ "vision_encoder.blocks.3.attn.norm.bias": "model-00001-of-00002.safetensors",
565
+ "vision_encoder.blocks.3.attn.norm.weight": "model-00001-of-00002.safetensors",
566
+ "vision_encoder.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
567
+ "vision_encoder.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
568
+ "vision_encoder.blocks.3.attn.q_proj.bias": "model-00001-of-00002.safetensors",
569
+ "vision_encoder.blocks.3.attn.q_proj.weight": "model-00001-of-00002.safetensors",
570
+ "vision_encoder.blocks.3.attn.v_proj.bias": "model-00001-of-00002.safetensors",
571
+ "vision_encoder.blocks.3.attn.v_proj.weight": "model-00001-of-00002.safetensors",
572
+ "vision_encoder.blocks.3.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
573
+ "vision_encoder.blocks.3.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
574
+ "vision_encoder.blocks.3.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
575
+ "vision_encoder.blocks.3.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
576
+ "vision_encoder.blocks.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
577
+ "vision_encoder.blocks.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
578
+ "vision_encoder.blocks.3.mlp.norm.bias": "model-00001-of-00002.safetensors",
579
+ "vision_encoder.blocks.3.mlp.norm.weight": "model-00001-of-00002.safetensors",
580
+ "vision_encoder.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
581
+ "vision_encoder.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
582
+ "vision_encoder.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
583
+ "vision_encoder.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
584
+ "vision_encoder.blocks.4.attn.k_proj.weight": "model-00001-of-00002.safetensors",
585
+ "vision_encoder.blocks.4.attn.norm.bias": "model-00001-of-00002.safetensors",
586
+ "vision_encoder.blocks.4.attn.norm.weight": "model-00001-of-00002.safetensors",
587
+ "vision_encoder.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
588
+ "vision_encoder.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
589
+ "vision_encoder.blocks.4.attn.q_proj.bias": "model-00001-of-00002.safetensors",
590
+ "vision_encoder.blocks.4.attn.q_proj.weight": "model-00001-of-00002.safetensors",
591
+ "vision_encoder.blocks.4.attn.v_proj.bias": "model-00001-of-00002.safetensors",
592
+ "vision_encoder.blocks.4.attn.v_proj.weight": "model-00001-of-00002.safetensors",
593
+ "vision_encoder.blocks.4.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
594
+ "vision_encoder.blocks.4.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
595
+ "vision_encoder.blocks.4.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
596
+ "vision_encoder.blocks.4.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
597
+ "vision_encoder.blocks.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
598
+ "vision_encoder.blocks.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
599
+ "vision_encoder.blocks.4.mlp.norm.bias": "model-00001-of-00002.safetensors",
600
+ "vision_encoder.blocks.4.mlp.norm.weight": "model-00001-of-00002.safetensors",
601
+ "vision_encoder.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
602
+ "vision_encoder.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
603
+ "vision_encoder.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
604
+ "vision_encoder.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
605
+ "vision_encoder.blocks.5.attn.k_proj.weight": "model-00001-of-00002.safetensors",
606
+ "vision_encoder.blocks.5.attn.norm.bias": "model-00001-of-00002.safetensors",
607
+ "vision_encoder.blocks.5.attn.norm.weight": "model-00001-of-00002.safetensors",
608
+ "vision_encoder.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
609
+ "vision_encoder.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
610
+ "vision_encoder.blocks.5.attn.q_proj.bias": "model-00001-of-00002.safetensors",
611
+ "vision_encoder.blocks.5.attn.q_proj.weight": "model-00001-of-00002.safetensors",
612
+ "vision_encoder.blocks.5.attn.v_proj.bias": "model-00001-of-00002.safetensors",
613
+ "vision_encoder.blocks.5.attn.v_proj.weight": "model-00001-of-00002.safetensors",
614
+ "vision_encoder.blocks.5.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
615
+ "vision_encoder.blocks.5.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
616
+ "vision_encoder.blocks.5.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
617
+ "vision_encoder.blocks.5.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
618
+ "vision_encoder.blocks.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
619
+ "vision_encoder.blocks.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
620
+ "vision_encoder.blocks.5.mlp.norm.bias": "model-00001-of-00002.safetensors",
621
+ "vision_encoder.blocks.5.mlp.norm.weight": "model-00001-of-00002.safetensors",
622
+ "vision_encoder.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
623
+ "vision_encoder.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
624
+ "vision_encoder.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
625
+ "vision_encoder.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
626
+ "vision_encoder.blocks.6.attn.k_proj.weight": "model-00001-of-00002.safetensors",
627
+ "vision_encoder.blocks.6.attn.norm.bias": "model-00001-of-00002.safetensors",
628
+ "vision_encoder.blocks.6.attn.norm.weight": "model-00001-of-00002.safetensors",
629
+ "vision_encoder.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
630
+ "vision_encoder.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
631
+ "vision_encoder.blocks.6.attn.q_proj.bias": "model-00001-of-00002.safetensors",
632
+ "vision_encoder.blocks.6.attn.q_proj.weight": "model-00001-of-00002.safetensors",
633
+ "vision_encoder.blocks.6.attn.v_proj.bias": "model-00001-of-00002.safetensors",
634
+ "vision_encoder.blocks.6.attn.v_proj.weight": "model-00001-of-00002.safetensors",
635
+ "vision_encoder.blocks.6.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
636
+ "vision_encoder.blocks.6.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
637
+ "vision_encoder.blocks.6.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
638
+ "vision_encoder.blocks.6.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
639
+ "vision_encoder.blocks.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
640
+ "vision_encoder.blocks.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
641
+ "vision_encoder.blocks.6.mlp.norm.bias": "model-00001-of-00002.safetensors",
642
+ "vision_encoder.blocks.6.mlp.norm.weight": "model-00001-of-00002.safetensors",
643
+ "vision_encoder.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
644
+ "vision_encoder.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
645
+ "vision_encoder.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
646
+ "vision_encoder.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
647
+ "vision_encoder.blocks.7.attn.k_proj.weight": "model-00001-of-00002.safetensors",
648
+ "vision_encoder.blocks.7.attn.norm.bias": "model-00001-of-00002.safetensors",
649
+ "vision_encoder.blocks.7.attn.norm.weight": "model-00001-of-00002.safetensors",
650
+ "vision_encoder.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
651
+ "vision_encoder.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
652
+ "vision_encoder.blocks.7.attn.q_proj.bias": "model-00001-of-00002.safetensors",
653
+ "vision_encoder.blocks.7.attn.q_proj.weight": "model-00001-of-00002.safetensors",
654
+ "vision_encoder.blocks.7.attn.v_proj.bias": "model-00001-of-00002.safetensors",
655
+ "vision_encoder.blocks.7.attn.v_proj.weight": "model-00001-of-00002.safetensors",
656
+ "vision_encoder.blocks.7.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
657
+ "vision_encoder.blocks.7.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
658
+ "vision_encoder.blocks.7.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
659
+ "vision_encoder.blocks.7.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
660
+ "vision_encoder.blocks.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
661
+ "vision_encoder.blocks.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
662
+ "vision_encoder.blocks.7.mlp.norm.bias": "model-00001-of-00002.safetensors",
663
+ "vision_encoder.blocks.7.mlp.norm.weight": "model-00001-of-00002.safetensors",
664
+ "vision_encoder.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
665
+ "vision_encoder.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
666
+ "vision_encoder.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
667
+ "vision_encoder.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
668
+ "vision_encoder.blocks.8.attn.k_proj.weight": "model-00001-of-00002.safetensors",
669
+ "vision_encoder.blocks.8.attn.norm.bias": "model-00001-of-00002.safetensors",
670
+ "vision_encoder.blocks.8.attn.norm.weight": "model-00001-of-00002.safetensors",
671
+ "vision_encoder.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
672
+ "vision_encoder.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
673
+ "vision_encoder.blocks.8.attn.q_proj.bias": "model-00001-of-00002.safetensors",
674
+ "vision_encoder.blocks.8.attn.q_proj.weight": "model-00001-of-00002.safetensors",
675
+ "vision_encoder.blocks.8.attn.v_proj.bias": "model-00001-of-00002.safetensors",
676
+ "vision_encoder.blocks.8.attn.v_proj.weight": "model-00001-of-00002.safetensors",
677
+ "vision_encoder.blocks.8.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
678
+ "vision_encoder.blocks.8.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
679
+ "vision_encoder.blocks.8.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
680
+ "vision_encoder.blocks.8.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
681
+ "vision_encoder.blocks.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
682
+ "vision_encoder.blocks.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
683
+ "vision_encoder.blocks.8.mlp.norm.bias": "model-00001-of-00002.safetensors",
684
+ "vision_encoder.blocks.8.mlp.norm.weight": "model-00001-of-00002.safetensors",
685
+ "vision_encoder.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
686
+ "vision_encoder.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
687
+ "vision_encoder.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
688
+ "vision_encoder.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
689
+ "vision_encoder.blocks.9.attn.k_proj.weight": "model-00001-of-00002.safetensors",
690
+ "vision_encoder.blocks.9.attn.norm.bias": "model-00001-of-00002.safetensors",
691
+ "vision_encoder.blocks.9.attn.norm.weight": "model-00001-of-00002.safetensors",
692
+ "vision_encoder.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
693
+ "vision_encoder.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
694
+ "vision_encoder.blocks.9.attn.q_proj.bias": "model-00001-of-00002.safetensors",
695
+ "vision_encoder.blocks.9.attn.q_proj.weight": "model-00001-of-00002.safetensors",
696
+ "vision_encoder.blocks.9.attn.v_proj.bias": "model-00001-of-00002.safetensors",
697
+ "vision_encoder.blocks.9.attn.v_proj.weight": "model-00001-of-00002.safetensors",
698
+ "vision_encoder.blocks.9.mlp.fc1_g.bias": "model-00001-of-00002.safetensors",
699
+ "vision_encoder.blocks.9.mlp.fc1_g.weight": "model-00001-of-00002.safetensors",
700
+ "vision_encoder.blocks.9.mlp.fc1_x.bias": "model-00001-of-00002.safetensors",
701
+ "vision_encoder.blocks.9.mlp.fc1_x.weight": "model-00001-of-00002.safetensors",
702
+ "vision_encoder.blocks.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
703
+ "vision_encoder.blocks.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
704
+ "vision_encoder.blocks.9.mlp.norm.bias": "model-00001-of-00002.safetensors",
705
+ "vision_encoder.blocks.9.mlp.norm.weight": "model-00001-of-00002.safetensors",
706
+ "vision_encoder.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
707
+ "vision_encoder.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
708
+ "vision_encoder.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
709
+ "vision_encoder.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
710
+ "vision_encoder.cls_token": "model-00001-of-00002.safetensors",
711
+ "vision_encoder.norm.bias": "model-00002-of-00002.safetensors",
712
+ "vision_encoder.norm.weight": "model-00002-of-00002.safetensors",
713
+ "vision_encoder.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
714
+ "vision_encoder.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
715
+ "vision_encoder.pos_embed": "model-00001-of-00002.safetensors"
716
+ }
717
+ }
checkpoint-final/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56f55cc388fdbff8bbfc2ca2fcf113e905357fc706a71a8e113380efaa064364
3
+ size 8144790622
checkpoint-final/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58250fe1dd84fd85660cee4bb7c7aca0811a7569cf941e6f4f9bfca28b2b4f62
3
+ size 1064
checkpoint-final/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-final/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08ce939e522ea614879ddb3fd2e44e03c23e1755c44e09d03a427027b54e53d4
3
+ size 4792
runs/Apr21_22-48-14_gpantaz-mamba-gpu3/events.out.tfevents.1713736112.gpantaz-mamba-gpu3.6464.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:175ab1bbe314b36fb9101c1f7fe0d09be42d1dfa6caef2a276f2e823a34bc41d
3
+ size 4661
runs/Apr21_23-10-33_gpantaz-mamba-gpu3/events.out.tfevents.1713737453.gpantaz-mamba-gpu3.9017.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49634f35430213c088a6f5f0a6f769499f9fd01faaae1721efcc87b08e5ea97b
3
+ size 7741
runs/Apr21_23-12-54_gpantaz-mamba-gpu3/events.out.tfevents.1713737592.gpantaz-mamba-gpu3.9956.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:158acc534471f3c41d594812aba8fd2e5195206439b9f579f1fa222399d9337f
3
+ size 113395
runs/Apr21_23-20-39_gpantaz-mamba-gpu3/events.out.tfevents.1713738057.gpantaz-mamba-gpu3.11832.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a988e32c1b70022deec0019e9791a91f6509ee600ae2ccb9ee681ecf64382d4c
3
+ size 6449431