Hugging Face's logo

nota-ai
/
phiva-4b-hf

Image-Text-to-Text
Transformers
Safetensors
English
llava
conversational
Inference Endpoints
Model card Files Community
jykim310 commited on
Commit
4d43620
•
1 Parent(s): 39c1bad

upload model

Browse files
Files changed (12) hide show
  1. added_tokens.json +14 -0
  2. config.json +47 -0
  3. generation_config.json +7 -0
  4. model-00001-of-00002.safetensors +3 -0
  5. model-00002-of-00002.safetensors +3 -0
  6. model.safetensors.index.json +405 -0
  7. preprocessor_config.json +28 -0
  8. processor_config.json +4 -0
  9. special_tokens_map.json +33 -0
  10. tokenizer.json +0 -0
  11. tokenizer.model +3 -0
  12. tokenizer_config.json +143 -0
added_tokens.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<image>": 32011,
3
+ "<|assistant|>": 32001,
4
+ "<|endoftext|>": 32000,
5
+ "<|end|>": 32007,
6
+ "<|placeholder1|>": 32002,
7
+ "<|placeholder2|>": 32003,
8
+ "<|placeholder3|>": 32004,
9
+ "<|placeholder4|>": 32005,
10
+ "<|placeholder5|>": 32008,
11
+ "<|placeholder6|>": 32009,
12
+ "<|system|>": 32006,
13
+ "<|user|>": 32010
14
+ }
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "phiva-4b-pretrained",
3
+ "architectures": [
4
+ "LlavaForConditionalGeneration"
5
+ ],
6
+ "ignore_index": -100,
7
+ "image_token_index": 32011,
8
+ "model_type": "llava",
9
+ "pad_token_id": 32000,
10
+ "projector_hidden_act": "gelu",
11
+ "text_config": {
12
+ "_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
13
+ "architectures": [
14
+ "Phi3ForCausalLM"
15
+ ],
16
+ "embd_pdrop": 0.0,
17
+ "eos_token_id": 32000,
18
+ "hidden_size": 3072,
19
+ "intermediate_size": 8192,
20
+ "max_position_embeddings": 131072,
21
+ "model_type": "phi3",
22
+ "original_max_position_embeddings": 4096,
23
+ "pad_token_id": 32000,
24
+ "resid_pdrop": 0.0,
25
+ "rms_norm_eps": 1e-06,
26
+ "sliding_window": null,
27
+ "torch_dtype": "float16",
28
+ "vocab_size": 32013
29
+ },
30
+ "tie_word_embeddings": false,
31
+ "torch_dtype": "float16",
32
+ "transformers_version": "4.42.3",
33
+ "vision_config": {
34
+ "hidden_size": 768,
35
+ "image_size": 224,
36
+ "intermediate_size": 3072,
37
+ "model_type": "clip_vision_model",
38
+ "num_attention_heads": 12,
39
+ "num_hidden_layers": 12,
40
+ "patch_size": 16,
41
+ "projection_dim": 512,
42
+ "vocab_size": 32013
43
+ },
44
+ "vision_feature_layer": -2,
45
+ "vision_feature_select_strategy": "default",
46
+ "vocab_size": 32013
47
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 32000,
5
+ "pad_token_id": 32000,
6
+ "transformers_version": "4.42.3"
7
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32a796a2fb58f579a0048eece3218a5813d7315092d6f6b29dfc472a9cf5d6fd
3
+ size 4997526968
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6685c50f96c19c8ee04d09b6cd0cadff9b606c41a57572e63c2d9578f4eda18d
3
+ size 2839262400
model.safetensors.index.json ADDED
@@ -0,0 +1,405 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 7836736512
4
+ },
5
+ "weight_map": {
6
+ "language_model.lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "language_model.model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
11
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
13
+ "language_model.model.layers.0.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
14
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
15
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
16
+ "language_model.model.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
17
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
18
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
19
+ "language_model.model.layers.1.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
20
+ "language_model.model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
21
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
22
+ "language_model.model.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
23
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
25
+ "language_model.model.layers.10.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
26
+ "language_model.model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
+ "language_model.model.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
29
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
30
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
31
+ "language_model.model.layers.11.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
32
+ "language_model.model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
33
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
34
+ "language_model.model.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
35
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
37
+ "language_model.model.layers.12.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
38
+ "language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
39
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
40
+ "language_model.model.layers.13.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
41
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
42
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
43
+ "language_model.model.layers.13.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
44
+ "language_model.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "language_model.model.layers.14.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
47
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
49
+ "language_model.model.layers.14.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
50
+ "language_model.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
51
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
52
+ "language_model.model.layers.15.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
53
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
55
+ "language_model.model.layers.15.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
56
+ "language_model.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
58
+ "language_model.model.layers.16.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
59
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
60
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
61
+ "language_model.model.layers.16.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
62
+ "language_model.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
+ "language_model.model.layers.17.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
65
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
66
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
67
+ "language_model.model.layers.17.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
68
+ "language_model.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
69
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
70
+ "language_model.model.layers.18.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
71
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
73
+ "language_model.model.layers.18.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
74
+ "language_model.model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
75
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
76
+ "language_model.model.layers.19.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
77
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
78
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
79
+ "language_model.model.layers.19.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
80
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "language_model.model.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
83
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
84
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
85
+ "language_model.model.layers.2.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
86
+ "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
87
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
88
+ "language_model.model.layers.20.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
89
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
90
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
91
+ "language_model.model.layers.20.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
92
+ "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
93
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
94
+ "language_model.model.layers.21.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
95
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
96
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
97
+ "language_model.model.layers.21.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
98
+ "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
99
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
100
+ "language_model.model.layers.22.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
101
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
102
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
103
+ "language_model.model.layers.22.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
104
+ "language_model.model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
105
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
106
+ "language_model.model.layers.23.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
107
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
108
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
109
+ "language_model.model.layers.23.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
110
+ "language_model.model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
111
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
112
+ "language_model.model.layers.24.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
113
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
114
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
115
+ "language_model.model.layers.24.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
116
+ "language_model.model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
117
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
118
+ "language_model.model.layers.25.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
119
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
120
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
121
+ "language_model.model.layers.25.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
122
+ "language_model.model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
123
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
124
+ "language_model.model.layers.26.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
125
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
126
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
127
+ "language_model.model.layers.26.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
128
+ "language_model.model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
129
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
130
+ "language_model.model.layers.27.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
131
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
132
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
133
+ "language_model.model.layers.27.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
134
+ "language_model.model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
135
+ "language_model.model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
136
+ "language_model.model.layers.28.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
137
+ "language_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
138
+ "language_model.model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
139
+ "language_model.model.layers.28.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
140
+ "language_model.model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
141
+ "language_model.model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
142
+ "language_model.model.layers.29.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
143
+ "language_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
144
+ "language_model.model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
145
+ "language_model.model.layers.29.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
146
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
147
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
148
+ "language_model.model.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
149
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
150
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
151
+ "language_model.model.layers.3.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
152
+ "language_model.model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
153
+ "language_model.model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
154
+ "language_model.model.layers.30.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
155
+ "language_model.model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
+ "language_model.model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
157
+ "language_model.model.layers.30.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
158
+ "language_model.model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
159
+ "language_model.model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
160
+ "language_model.model.layers.31.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
161
+ "language_model.model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
162
+ "language_model.model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
163
+ "language_model.model.layers.31.self_attn.qkv_proj.weight": "model-00002-of-00002.safetensors",
164
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
165
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
166
+ "language_model.model.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
167
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
168
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
169
+ "language_model.model.layers.4.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
170
+ "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
171
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
172
+ "language_model.model.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
173
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
174
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
175
+ "language_model.model.layers.5.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
176
+ "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
177
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
178
+ "language_model.model.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
179
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
180
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
181
+ "language_model.model.layers.6.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
182
+ "language_model.model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
183
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
184
+ "language_model.model.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
185
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
186
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
187
+ "language_model.model.layers.7.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
188
+ "language_model.model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
189
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
190
+ "language_model.model.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
191
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
192
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
193
+ "language_model.model.layers.8.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
194
+ "language_model.model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
195
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
196
+ "language_model.model.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
197
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
198
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
199
+ "language_model.model.layers.9.self_attn.qkv_proj.weight": "model-00001-of-00002.safetensors",
200
+ "language_model.model.norm.weight": "model-00002-of-00002.safetensors",
201
+ "multi_modal_projector.linear_1.bias": "model-00001-of-00002.safetensors",
202
+ "multi_modal_projector.linear_1.weight": "model-00001-of-00002.safetensors",
203
+ "multi_modal_projector.linear_2.bias": "model-00001-of-00002.safetensors",
204
+ "multi_modal_projector.linear_2.weight": "model-00001-of-00002.safetensors",
205
+ "vision_tower.vision_model.embeddings.class_embedding": "model-00001-of-00002.safetensors",
206
+ "vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00001-of-00002.safetensors",
207
+ "vision_tower.vision_model.embeddings.position_embedding.weight": "model-00001-of-00002.safetensors",
208
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
209
+ "vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
210
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
211
+ "vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
212
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
213
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
214
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
215
+ "vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
216
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
217
+ "vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
218
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
219
+ "vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
220
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
221
+ "vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
222
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
223
+ "vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
224
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
225
+ "vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
226
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
227
+ "vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
228
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
229
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
230
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
231
+ "vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
232
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
233
+ "vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
234
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
235
+ "vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
236
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
237
+ "vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
238
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
239
+ "vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
240
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
241
+ "vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
242
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
243
+ "vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
244
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
245
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
246
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
247
+ "vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
248
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
249
+ "vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
250
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
251
+ "vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
252
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
253
+ "vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
254
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
255
+ "vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
256
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
257
+ "vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
258
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
259
+ "vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
260
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
261
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
262
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
263
+ "vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
264
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
265
+ "vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
266
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
267
+ "vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
268
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
269
+ "vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
270
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
271
+ "vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
272
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
273
+ "vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
274
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
275
+ "vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
276
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
277
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
278
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
279
+ "vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
280
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
281
+ "vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
282
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
283
+ "vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
284
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
285
+ "vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
286
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
287
+ "vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
288
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
289
+ "vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
290
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
291
+ "vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
292
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
293
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
294
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
295
+ "vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
296
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
297
+ "vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
298
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
299
+ "vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
300
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
301
+ "vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
302
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
303
+ "vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
304
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
305
+ "vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
306
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
307
+ "vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
308
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
309
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
310
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
311
+ "vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
312
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
313
+ "vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
314
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
315
+ "vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
316
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
317
+ "vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
318
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
319
+ "vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
320
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
321
+ "vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
322
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
323
+ "vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
324
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
325
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
326
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
327
+ "vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
328
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
329
+ "vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
330
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
331
+ "vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
332
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
333
+ "vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
334
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
335
+ "vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
336
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
337
+ "vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
338
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
339
+ "vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
340
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
341
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
342
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
343
+ "vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
344
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
345
+ "vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
346
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
347
+ "vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
348
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
349
+ "vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
350
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
351
+ "vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
352
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
353
+ "vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
354
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
355
+ "vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
356
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
357
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
358
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
359
+ "vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
360
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
361
+ "vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
362
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
363
+ "vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
364
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
365
+ "vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
366
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
367
+ "vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
368
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
369
+ "vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
370
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
371
+ "vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
372
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
373
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
374
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
375
+ "vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
376
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
377
+ "vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
378
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
379
+ "vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
380
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
381
+ "vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
382
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
383
+ "vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
384
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
385
+ "vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
386
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
387
+ "vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
388
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
389
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
390
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
391
+ "vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
392
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
393
+ "vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
394
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
395
+ "vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
396
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
397
+ "vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
398
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
399
+ "vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
400
+ "vision_tower.vision_model.post_layernorm.bias": "model-00001-of-00002.safetensors",
401
+ "vision_tower.vision_model.post_layernorm.weight": "model-00001-of-00002.safetensors",
402
+ "vision_tower.vision_model.pre_layrnorm.bias": "model-00001-of-00002.safetensors",
403
+ "vision_tower.vision_model.pre_layrnorm.weight": "model-00001-of-00002.safetensors"
404
+ }
405
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "processor_class": "LlavaProcessor",
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "shortest_edge": 224
27
+ }
28
+ }
processor_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "chat_template": null,
3
+ "processor_class": "LlavaProcessor"
4
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<image>"
4
+ ],
5
+ "bos_token": {
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "pad_token": {
20
+ "content": "<|endoftext|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,143 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": false
29
+ },
30
+ "32000": {
31
+ "content": "<|endoftext|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|assistant|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|placeholder1|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|placeholder2|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|placeholder3|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|placeholder4|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|system|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|placeholder5|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|placeholder6|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": true,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|user|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": true,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "32011": {
119
+ "content": "<image>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ }
126
+ },
127
+ "additional_special_tokens": [
128
+ "<image>"
129
+ ],
130
+ "bos_token": "<s>",
131
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
132
+ "clean_up_tokenization_spaces": false,
133
+ "eos_token": "<|endoftext|>",
134
+ "legacy": false,
135
+ "model_max_length": 4096,
136
+ "pad_token": "<|endoftext|>",
137
+ "padding_side": "left",
138
+ "processor_class": "LlavaProcessor",
139
+ "sp_model_kwargs": {},
140
+ "tokenizer_class": "LlamaTokenizer",
141
+ "unk_token": "<unk>",
142
+ "use_default_system_prompt": false
143
+ }