xiechunyu commited on
Commit
16f1801
1 Parent(s): 3d61ed0

first commit

Browse files
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "qh360_vl-8B",
3
+ "architectures": [
4
+ "QH360_VL_LlamaForCausalLM"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "modeling_360vl.QH360_VLConfig",
8
+ "AutoModelForCausalLM": "modeling_360vl.QH360_VL_LlamaForCausalLM"
9
+ },
10
+ "attention_bias": false,
11
+ "attention_dropout": 0.0,
12
+ "bos_token_id": 128000,
13
+ "eos_token_id": 128001,
14
+ "freeze_mm_mlp_adapter": false,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 4096,
17
+ "image_aspect_ratio": "pad",
18
+ "image_grid_pinpoints": null,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 14336,
21
+ "max_position_embeddings": 8192,
22
+ "mm_hidden_size": 1024,
23
+ "mm_num_tokens": 577,
24
+ "mm_projector_config": "qh360_vl-8B/proj_config.json",
25
+ "mm_projector_lr": null,
26
+ "mm_projector_type": "c-abs",
27
+ "mm_use_im_patch_token": false,
28
+ "mm_use_im_start_end": false,
29
+ "mm_vision_select_feature": "patch",
30
+ "mm_vision_select_layer": -2,
31
+ "mm_vision_tower": "openai/clip-vit-large-patch14-336",
32
+ "model_type": "QH_360VL",
33
+ "num_attention_heads": 32,
34
+ "num_hidden_layers": 32,
35
+ "num_key_value_heads": 8,
36
+ "pretraining_tp": 1,
37
+ "proj_2": true,
38
+ "rms_norm_eps": 1e-05,
39
+ "rope_scaling": null,
40
+ "rope_theta": 500000.0,
41
+ "tie_word_embeddings": false,
42
+ "torch_dtype": "bfloat16",
43
+ "transformers_version": "4.37.2",
44
+ "tune_mm_mlp_adapter": false,
45
+ "use_cache": true,
46
+ "use_mm_proj": true,
47
+ "vocab_size": 128256
48
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "eos_token_id": 128001,
5
+ "transformers_version": "4.37.2"
6
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecd95a8decd9193c4d5e62cd3e2310705ab0578ad3b70dca419ecdcc4db07070
3
+ size 4976698672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bec7364ce42fd08396ec3f33bbcb9cfcdeaa0c429abf166ccc7f69e2784a550
3
+ size 4999802720
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:962a9bfede9380c2670709835b9a965e6fb5135de2545e5730b7683a5eed9621
3
+ size 4915916176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:270108da03eac6c382f798f4f67d6bf5f8471fba109820caf3759b1b3efcde61
3
+ size 1924831600
model.safetensors.index.json ADDED
@@ -0,0 +1,855 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16817133568
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.mm_projector_ctt.net.0.b1.conv1.bn.bias": "model-00004-of-00004.safetensors",
297
+ "model.mm_projector_ctt.net.0.b1.conv1.bn.weight": "model-00004-of-00004.safetensors",
298
+ "model.mm_projector_ctt.net.0.b1.conv1.conv.weight": "model-00004-of-00004.safetensors",
299
+ "model.mm_projector_ctt.net.0.b1.conv2.bn.bias": "model-00004-of-00004.safetensors",
300
+ "model.mm_projector_ctt.net.0.b1.conv2.bn.weight": "model-00004-of-00004.safetensors",
301
+ "model.mm_projector_ctt.net.0.b1.conv2.conv.weight": "model-00004-of-00004.safetensors",
302
+ "model.mm_projector_ctt.net.0.b1.conv3.bn.bias": "model-00004-of-00004.safetensors",
303
+ "model.mm_projector_ctt.net.0.b1.conv3.bn.weight": "model-00004-of-00004.safetensors",
304
+ "model.mm_projector_ctt.net.0.b1.conv3.conv.weight": "model-00004-of-00004.safetensors",
305
+ "model.mm_projector_ctt.net.0.b1.se.fc1.bias": "model-00004-of-00004.safetensors",
306
+ "model.mm_projector_ctt.net.0.b1.se.fc1.weight": "model-00004-of-00004.safetensors",
307
+ "model.mm_projector_ctt.net.0.b1.se.fc2.bias": "model-00004-of-00004.safetensors",
308
+ "model.mm_projector_ctt.net.0.b1.se.fc2.weight": "model-00004-of-00004.safetensors",
309
+ "model.mm_projector_ctt.net.0.b2.conv1.bn.bias": "model-00004-of-00004.safetensors",
310
+ "model.mm_projector_ctt.net.0.b2.conv1.bn.weight": "model-00004-of-00004.safetensors",
311
+ "model.mm_projector_ctt.net.0.b2.conv1.conv.weight": "model-00004-of-00004.safetensors",
312
+ "model.mm_projector_ctt.net.0.b2.conv2.bn.bias": "model-00004-of-00004.safetensors",
313
+ "model.mm_projector_ctt.net.0.b2.conv2.bn.weight": "model-00004-of-00004.safetensors",
314
+ "model.mm_projector_ctt.net.0.b2.conv2.conv.weight": "model-00004-of-00004.safetensors",
315
+ "model.mm_projector_ctt.net.0.b2.conv3.bn.bias": "model-00004-of-00004.safetensors",
316
+ "model.mm_projector_ctt.net.0.b2.conv3.bn.weight": "model-00004-of-00004.safetensors",
317
+ "model.mm_projector_ctt.net.0.b2.conv3.conv.weight": "model-00004-of-00004.safetensors",
318
+ "model.mm_projector_ctt.net.0.b2.se.fc1.bias": "model-00004-of-00004.safetensors",
319
+ "model.mm_projector_ctt.net.0.b2.se.fc1.weight": "model-00004-of-00004.safetensors",
320
+ "model.mm_projector_ctt.net.0.b2.se.fc2.bias": "model-00004-of-00004.safetensors",
321
+ "model.mm_projector_ctt.net.0.b2.se.fc2.weight": "model-00004-of-00004.safetensors",
322
+ "model.mm_projector_ctt.net.0.b3.conv1.bn.bias": "model-00004-of-00004.safetensors",
323
+ "model.mm_projector_ctt.net.0.b3.conv1.bn.weight": "model-00004-of-00004.safetensors",
324
+ "model.mm_projector_ctt.net.0.b3.conv1.conv.weight": "model-00004-of-00004.safetensors",
325
+ "model.mm_projector_ctt.net.0.b3.conv2.bn.bias": "model-00004-of-00004.safetensors",
326
+ "model.mm_projector_ctt.net.0.b3.conv2.bn.weight": "model-00004-of-00004.safetensors",
327
+ "model.mm_projector_ctt.net.0.b3.conv2.conv.weight": "model-00004-of-00004.safetensors",
328
+ "model.mm_projector_ctt.net.0.b3.conv3.bn.bias": "model-00004-of-00004.safetensors",
329
+ "model.mm_projector_ctt.net.0.b3.conv3.bn.weight": "model-00004-of-00004.safetensors",
330
+ "model.mm_projector_ctt.net.0.b3.conv3.conv.weight": "model-00004-of-00004.safetensors",
331
+ "model.mm_projector_ctt.net.0.b3.se.fc1.bias": "model-00004-of-00004.safetensors",
332
+ "model.mm_projector_ctt.net.0.b3.se.fc1.weight": "model-00004-of-00004.safetensors",
333
+ "model.mm_projector_ctt.net.0.b3.se.fc2.bias": "model-00004-of-00004.safetensors",
334
+ "model.mm_projector_ctt.net.0.b3.se.fc2.weight": "model-00004-of-00004.safetensors",
335
+ "model.mm_projector_ctt.net.2.b1.conv1.bn.bias": "model-00004-of-00004.safetensors",
336
+ "model.mm_projector_ctt.net.2.b1.conv1.bn.weight": "model-00004-of-00004.safetensors",
337
+ "model.mm_projector_ctt.net.2.b1.conv1.conv.weight": "model-00004-of-00004.safetensors",
338
+ "model.mm_projector_ctt.net.2.b1.conv2.bn.bias": "model-00004-of-00004.safetensors",
339
+ "model.mm_projector_ctt.net.2.b1.conv2.bn.weight": "model-00004-of-00004.safetensors",
340
+ "model.mm_projector_ctt.net.2.b1.conv2.conv.weight": "model-00004-of-00004.safetensors",
341
+ "model.mm_projector_ctt.net.2.b1.conv3.bn.bias": "model-00004-of-00004.safetensors",
342
+ "model.mm_projector_ctt.net.2.b1.conv3.bn.weight": "model-00004-of-00004.safetensors",
343
+ "model.mm_projector_ctt.net.2.b1.conv3.conv.weight": "model-00004-of-00004.safetensors",
344
+ "model.mm_projector_ctt.net.2.b1.se.fc1.bias": "model-00004-of-00004.safetensors",
345
+ "model.mm_projector_ctt.net.2.b1.se.fc1.weight": "model-00004-of-00004.safetensors",
346
+ "model.mm_projector_ctt.net.2.b1.se.fc2.bias": "model-00004-of-00004.safetensors",
347
+ "model.mm_projector_ctt.net.2.b1.se.fc2.weight": "model-00004-of-00004.safetensors",
348
+ "model.mm_projector_ctt.net.2.b2.conv1.bn.bias": "model-00004-of-00004.safetensors",
349
+ "model.mm_projector_ctt.net.2.b2.conv1.bn.weight": "model-00004-of-00004.safetensors",
350
+ "model.mm_projector_ctt.net.2.b2.conv1.conv.weight": "model-00004-of-00004.safetensors",
351
+ "model.mm_projector_ctt.net.2.b2.conv2.bn.bias": "model-00004-of-00004.safetensors",
352
+ "model.mm_projector_ctt.net.2.b2.conv2.bn.weight": "model-00004-of-00004.safetensors",
353
+ "model.mm_projector_ctt.net.2.b2.conv2.conv.weight": "model-00004-of-00004.safetensors",
354
+ "model.mm_projector_ctt.net.2.b2.conv3.bn.bias": "model-00004-of-00004.safetensors",
355
+ "model.mm_projector_ctt.net.2.b2.conv3.bn.weight": "model-00004-of-00004.safetensors",
356
+ "model.mm_projector_ctt.net.2.b2.conv3.conv.weight": "model-00004-of-00004.safetensors",
357
+ "model.mm_projector_ctt.net.2.b2.se.fc1.bias": "model-00004-of-00004.safetensors",
358
+ "model.mm_projector_ctt.net.2.b2.se.fc1.weight": "model-00004-of-00004.safetensors",
359
+ "model.mm_projector_ctt.net.2.b2.se.fc2.bias": "model-00004-of-00004.safetensors",
360
+ "model.mm_projector_ctt.net.2.b2.se.fc2.weight": "model-00004-of-00004.safetensors",
361
+ "model.mm_projector_ctt.net.2.b3.conv1.bn.bias": "model-00004-of-00004.safetensors",
362
+ "model.mm_projector_ctt.net.2.b3.conv1.bn.weight": "model-00004-of-00004.safetensors",
363
+ "model.mm_projector_ctt.net.2.b3.conv1.conv.weight": "model-00004-of-00004.safetensors",
364
+ "model.mm_projector_ctt.net.2.b3.conv2.bn.bias": "model-00004-of-00004.safetensors",
365
+ "model.mm_projector_ctt.net.2.b3.conv2.bn.weight": "model-00004-of-00004.safetensors",
366
+ "model.mm_projector_ctt.net.2.b3.conv2.conv.weight": "model-00004-of-00004.safetensors",
367
+ "model.mm_projector_ctt.net.2.b3.conv3.bn.bias": "model-00004-of-00004.safetensors",
368
+ "model.mm_projector_ctt.net.2.b3.conv3.bn.weight": "model-00004-of-00004.safetensors",
369
+ "model.mm_projector_ctt.net.2.b3.conv3.conv.weight": "model-00004-of-00004.safetensors",
370
+ "model.mm_projector_ctt.net.2.b3.se.fc1.bias": "model-00004-of-00004.safetensors",
371
+ "model.mm_projector_ctt.net.2.b3.se.fc1.weight": "model-00004-of-00004.safetensors",
372
+ "model.mm_projector_ctt.net.2.b3.se.fc2.bias": "model-00004-of-00004.safetensors",
373
+ "model.mm_projector_ctt.net.2.b3.se.fc2.weight": "model-00004-of-00004.safetensors",
374
+ "model.mm_projector_ctt.pos_emb": "model-00004-of-00004.safetensors",
375
+ "model.mm_projector_ctt.readout.0.bias": "model-00004-of-00004.safetensors",
376
+ "model.mm_projector_ctt.readout.0.weight": "model-00004-of-00004.safetensors",
377
+ "model.mm_projector_ctt.readout.2.bias": "model-00004-of-00004.safetensors",
378
+ "model.mm_projector_ctt.readout.2.weight": "model-00004-of-00004.safetensors",
379
+ "model.mm_projector_ori.net.0.b1.conv1.bn.bias": "model-00004-of-00004.safetensors",
380
+ "model.mm_projector_ori.net.0.b1.conv1.bn.weight": "model-00004-of-00004.safetensors",
381
+ "model.mm_projector_ori.net.0.b1.conv1.conv.weight": "model-00004-of-00004.safetensors",
382
+ "model.mm_projector_ori.net.0.b1.conv2.bn.bias": "model-00004-of-00004.safetensors",
383
+ "model.mm_projector_ori.net.0.b1.conv2.bn.weight": "model-00004-of-00004.safetensors",
384
+ "model.mm_projector_ori.net.0.b1.conv2.conv.weight": "model-00004-of-00004.safetensors",
385
+ "model.mm_projector_ori.net.0.b1.conv3.bn.bias": "model-00004-of-00004.safetensors",
386
+ "model.mm_projector_ori.net.0.b1.conv3.bn.weight": "model-00004-of-00004.safetensors",
387
+ "model.mm_projector_ori.net.0.b1.conv3.conv.weight": "model-00004-of-00004.safetensors",
388
+ "model.mm_projector_ori.net.0.b1.se.fc1.bias": "model-00004-of-00004.safetensors",
389
+ "model.mm_projector_ori.net.0.b1.se.fc1.weight": "model-00004-of-00004.safetensors",
390
+ "model.mm_projector_ori.net.0.b1.se.fc2.bias": "model-00004-of-00004.safetensors",
391
+ "model.mm_projector_ori.net.0.b1.se.fc2.weight": "model-00004-of-00004.safetensors",
392
+ "model.mm_projector_ori.net.0.b2.conv1.bn.bias": "model-00004-of-00004.safetensors",
393
+ "model.mm_projector_ori.net.0.b2.conv1.bn.weight": "model-00004-of-00004.safetensors",
394
+ "model.mm_projector_ori.net.0.b2.conv1.conv.weight": "model-00004-of-00004.safetensors",
395
+ "model.mm_projector_ori.net.0.b2.conv2.bn.bias": "model-00004-of-00004.safetensors",
396
+ "model.mm_projector_ori.net.0.b2.conv2.bn.weight": "model-00004-of-00004.safetensors",
397
+ "model.mm_projector_ori.net.0.b2.conv2.conv.weight": "model-00004-of-00004.safetensors",
398
+ "model.mm_projector_ori.net.0.b2.conv3.bn.bias": "model-00004-of-00004.safetensors",
399
+ "model.mm_projector_ori.net.0.b2.conv3.bn.weight": "model-00004-of-00004.safetensors",
400
+ "model.mm_projector_ori.net.0.b2.conv3.conv.weight": "model-00004-of-00004.safetensors",
401
+ "model.mm_projector_ori.net.0.b2.se.fc1.bias": "model-00004-of-00004.safetensors",
402
+ "model.mm_projector_ori.net.0.b2.se.fc1.weight": "model-00004-of-00004.safetensors",
403
+ "model.mm_projector_ori.net.0.b2.se.fc2.bias": "model-00004-of-00004.safetensors",
404
+ "model.mm_projector_ori.net.0.b2.se.fc2.weight": "model-00004-of-00004.safetensors",
405
+ "model.mm_projector_ori.net.0.b3.conv1.bn.bias": "model-00004-of-00004.safetensors",
406
+ "model.mm_projector_ori.net.0.b3.conv1.bn.weight": "model-00004-of-00004.safetensors",
407
+ "model.mm_projector_ori.net.0.b3.conv1.conv.weight": "model-00004-of-00004.safetensors",
408
+ "model.mm_projector_ori.net.0.b3.conv2.bn.bias": "model-00004-of-00004.safetensors",
409
+ "model.mm_projector_ori.net.0.b3.conv2.bn.weight": "model-00004-of-00004.safetensors",
410
+ "model.mm_projector_ori.net.0.b3.conv2.conv.weight": "model-00004-of-00004.safetensors",
411
+ "model.mm_projector_ori.net.0.b3.conv3.bn.bias": "model-00004-of-00004.safetensors",
412
+ "model.mm_projector_ori.net.0.b3.conv3.bn.weight": "model-00004-of-00004.safetensors",
413
+ "model.mm_projector_ori.net.0.b3.conv3.conv.weight": "model-00004-of-00004.safetensors",
414
+ "model.mm_projector_ori.net.0.b3.se.fc1.bias": "model-00004-of-00004.safetensors",
415
+ "model.mm_projector_ori.net.0.b3.se.fc1.weight": "model-00004-of-00004.safetensors",
416
+ "model.mm_projector_ori.net.0.b3.se.fc2.bias": "model-00004-of-00004.safetensors",
417
+ "model.mm_projector_ori.net.0.b3.se.fc2.weight": "model-00004-of-00004.safetensors",
418
+ "model.mm_projector_ori.net.2.b1.conv1.bn.bias": "model-00004-of-00004.safetensors",
419
+ "model.mm_projector_ori.net.2.b1.conv1.bn.weight": "model-00004-of-00004.safetensors",
420
+ "model.mm_projector_ori.net.2.b1.conv1.conv.weight": "model-00004-of-00004.safetensors",
421
+ "model.mm_projector_ori.net.2.b1.conv2.bn.bias": "model-00004-of-00004.safetensors",
422
+ "model.mm_projector_ori.net.2.b1.conv2.bn.weight": "model-00004-of-00004.safetensors",
423
+ "model.mm_projector_ori.net.2.b1.conv2.conv.weight": "model-00004-of-00004.safetensors",
424
+ "model.mm_projector_ori.net.2.b1.conv3.bn.bias": "model-00004-of-00004.safetensors",
425
+ "model.mm_projector_ori.net.2.b1.conv3.bn.weight": "model-00004-of-00004.safetensors",
426
+ "model.mm_projector_ori.net.2.b1.conv3.conv.weight": "model-00004-of-00004.safetensors",
427
+ "model.mm_projector_ori.net.2.b1.se.fc1.bias": "model-00004-of-00004.safetensors",
428
+ "model.mm_projector_ori.net.2.b1.se.fc1.weight": "model-00004-of-00004.safetensors",
429
+ "model.mm_projector_ori.net.2.b1.se.fc2.bias": "model-00004-of-00004.safetensors",
430
+ "model.mm_projector_ori.net.2.b1.se.fc2.weight": "model-00004-of-00004.safetensors",
431
+ "model.mm_projector_ori.net.2.b2.conv1.bn.bias": "model-00004-of-00004.safetensors",
432
+ "model.mm_projector_ori.net.2.b2.conv1.bn.weight": "model-00004-of-00004.safetensors",
433
+ "model.mm_projector_ori.net.2.b2.conv1.conv.weight": "model-00004-of-00004.safetensors",
434
+ "model.mm_projector_ori.net.2.b2.conv2.bn.bias": "model-00004-of-00004.safetensors",
435
+ "model.mm_projector_ori.net.2.b2.conv2.bn.weight": "model-00004-of-00004.safetensors",
436
+ "model.mm_projector_ori.net.2.b2.conv2.conv.weight": "model-00004-of-00004.safetensors",
437
+ "model.mm_projector_ori.net.2.b2.conv3.bn.bias": "model-00004-of-00004.safetensors",
438
+ "model.mm_projector_ori.net.2.b2.conv3.bn.weight": "model-00004-of-00004.safetensors",
439
+ "model.mm_projector_ori.net.2.b2.conv3.conv.weight": "model-00004-of-00004.safetensors",
440
+ "model.mm_projector_ori.net.2.b2.se.fc1.bias": "model-00004-of-00004.safetensors",
441
+ "model.mm_projector_ori.net.2.b2.se.fc1.weight": "model-00004-of-00004.safetensors",
442
+ "model.mm_projector_ori.net.2.b2.se.fc2.bias": "model-00004-of-00004.safetensors",
443
+ "model.mm_projector_ori.net.2.b2.se.fc2.weight": "model-00004-of-00004.safetensors",
444
+ "model.mm_projector_ori.net.2.b3.conv1.bn.bias": "model-00004-of-00004.safetensors",
445
+ "model.mm_projector_ori.net.2.b3.conv1.bn.weight": "model-00004-of-00004.safetensors",
446
+ "model.mm_projector_ori.net.2.b3.conv1.conv.weight": "model-00004-of-00004.safetensors",
447
+ "model.mm_projector_ori.net.2.b3.conv2.bn.bias": "model-00004-of-00004.safetensors",
448
+ "model.mm_projector_ori.net.2.b3.conv2.bn.weight": "model-00004-of-00004.safetensors",
449
+ "model.mm_projector_ori.net.2.b3.conv2.conv.weight": "model-00004-of-00004.safetensors",
450
+ "model.mm_projector_ori.net.2.b3.conv3.bn.bias": "model-00004-of-00004.safetensors",
451
+ "model.mm_projector_ori.net.2.b3.conv3.bn.weight": "model-00004-of-00004.safetensors",
452
+ "model.mm_projector_ori.net.2.b3.conv3.conv.weight": "model-00004-of-00004.safetensors",
453
+ "model.mm_projector_ori.net.2.b3.se.fc1.bias": "model-00004-of-00004.safetensors",
454
+ "model.mm_projector_ori.net.2.b3.se.fc1.weight": "model-00004-of-00004.safetensors",
455
+ "model.mm_projector_ori.net.2.b3.se.fc2.bias": "model-00004-of-00004.safetensors",
456
+ "model.mm_projector_ori.net.2.b3.se.fc2.weight": "model-00004-of-00004.safetensors",
457
+ "model.mm_projector_ori.pos_emb": "model-00004-of-00004.safetensors",
458
+ "model.mm_projector_ori.readout.0.bias": "model-00004-of-00004.safetensors",
459
+ "model.mm_projector_ori.readout.0.weight": "model-00004-of-00004.safetensors",
460
+ "model.mm_projector_ori.readout.2.bias": "model-00004-of-00004.safetensors",
461
+ "model.mm_projector_ori.readout.2.weight": "model-00004-of-00004.safetensors",
462
+ "model.norm.weight": "model-00004-of-00004.safetensors",
463
+ "model.vision_tower.vision_tower.vision_model.embeddings.class_embedding": "model-00004-of-00004.safetensors",
464
+ "model.vision_tower.vision_tower.vision_model.embeddings.patch_embedding.weight": "model-00004-of-00004.safetensors",
465
+ "model.vision_tower.vision_tower.vision_model.embeddings.position_embedding.weight": "model-00004-of-00004.safetensors",
466
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.bias": "model-00004-of-00004.safetensors",
467
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm1.weight": "model-00004-of-00004.safetensors",
468
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.bias": "model-00004-of-00004.safetensors",
469
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.layer_norm2.weight": "model-00004-of-00004.safetensors",
470
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.bias": "model-00004-of-00004.safetensors",
471
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc1.weight": "model-00004-of-00004.safetensors",
472
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.bias": "model-00004-of-00004.safetensors",
473
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.mlp.fc2.weight": "model-00004-of-00004.safetensors",
474
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
475
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
476
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
477
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
478
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
479
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
480
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
481
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
482
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.bias": "model-00004-of-00004.safetensors",
483
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm1.weight": "model-00004-of-00004.safetensors",
484
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.bias": "model-00004-of-00004.safetensors",
485
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.layer_norm2.weight": "model-00004-of-00004.safetensors",
486
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.bias": "model-00004-of-00004.safetensors",
487
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc1.weight": "model-00004-of-00004.safetensors",
488
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.bias": "model-00004-of-00004.safetensors",
489
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.mlp.fc2.weight": "model-00004-of-00004.safetensors",
490
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
491
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
492
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
493
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
494
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
495
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
496
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
497
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
498
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.bias": "model-00004-of-00004.safetensors",
499
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm1.weight": "model-00004-of-00004.safetensors",
500
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.bias": "model-00004-of-00004.safetensors",
501
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.layer_norm2.weight": "model-00004-of-00004.safetensors",
502
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.bias": "model-00004-of-00004.safetensors",
503
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc1.weight": "model-00004-of-00004.safetensors",
504
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.bias": "model-00004-of-00004.safetensors",
505
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.mlp.fc2.weight": "model-00004-of-00004.safetensors",
506
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
507
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
508
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
509
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
510
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
511
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
512
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
513
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.10.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
514
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.bias": "model-00004-of-00004.safetensors",
515
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm1.weight": "model-00004-of-00004.safetensors",
516
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.bias": "model-00004-of-00004.safetensors",
517
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.layer_norm2.weight": "model-00004-of-00004.safetensors",
518
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.bias": "model-00004-of-00004.safetensors",
519
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc1.weight": "model-00004-of-00004.safetensors",
520
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.bias": "model-00004-of-00004.safetensors",
521
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.mlp.fc2.weight": "model-00004-of-00004.safetensors",
522
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
523
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
524
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
525
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
526
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
527
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
528
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
529
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.11.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
530
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.bias": "model-00004-of-00004.safetensors",
531
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm1.weight": "model-00004-of-00004.safetensors",
532
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.bias": "model-00004-of-00004.safetensors",
533
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.layer_norm2.weight": "model-00004-of-00004.safetensors",
534
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.bias": "model-00004-of-00004.safetensors",
535
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc1.weight": "model-00004-of-00004.safetensors",
536
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.bias": "model-00004-of-00004.safetensors",
537
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.mlp.fc2.weight": "model-00004-of-00004.safetensors",
538
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
539
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
540
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
541
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
542
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
543
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
544
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
545
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.12.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
546
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.bias": "model-00004-of-00004.safetensors",
547
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm1.weight": "model-00004-of-00004.safetensors",
548
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.bias": "model-00004-of-00004.safetensors",
549
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.layer_norm2.weight": "model-00004-of-00004.safetensors",
550
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.bias": "model-00004-of-00004.safetensors",
551
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc1.weight": "model-00004-of-00004.safetensors",
552
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.bias": "model-00004-of-00004.safetensors",
553
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.mlp.fc2.weight": "model-00004-of-00004.safetensors",
554
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
555
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
556
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
557
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
558
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
559
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
560
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
561
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.13.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
562
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.bias": "model-00004-of-00004.safetensors",
563
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm1.weight": "model-00004-of-00004.safetensors",
564
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.bias": "model-00004-of-00004.safetensors",
565
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.layer_norm2.weight": "model-00004-of-00004.safetensors",
566
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.bias": "model-00004-of-00004.safetensors",
567
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc1.weight": "model-00004-of-00004.safetensors",
568
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.bias": "model-00004-of-00004.safetensors",
569
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.mlp.fc2.weight": "model-00004-of-00004.safetensors",
570
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
571
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
572
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
573
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
574
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
575
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
576
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
577
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.14.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
578
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.bias": "model-00004-of-00004.safetensors",
579
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm1.weight": "model-00004-of-00004.safetensors",
580
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.bias": "model-00004-of-00004.safetensors",
581
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.layer_norm2.weight": "model-00004-of-00004.safetensors",
582
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.bias": "model-00004-of-00004.safetensors",
583
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc1.weight": "model-00004-of-00004.safetensors",
584
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.bias": "model-00004-of-00004.safetensors",
585
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.mlp.fc2.weight": "model-00004-of-00004.safetensors",
586
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
587
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
588
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
589
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
590
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
591
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
592
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
593
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.15.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
594
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.bias": "model-00004-of-00004.safetensors",
595
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm1.weight": "model-00004-of-00004.safetensors",
596
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.bias": "model-00004-of-00004.safetensors",
597
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.layer_norm2.weight": "model-00004-of-00004.safetensors",
598
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.bias": "model-00004-of-00004.safetensors",
599
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc1.weight": "model-00004-of-00004.safetensors",
600
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.bias": "model-00004-of-00004.safetensors",
601
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.mlp.fc2.weight": "model-00004-of-00004.safetensors",
602
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
603
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
604
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
605
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
606
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
607
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
608
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
609
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.16.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
610
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.bias": "model-00004-of-00004.safetensors",
611
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm1.weight": "model-00004-of-00004.safetensors",
612
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.bias": "model-00004-of-00004.safetensors",
613
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.layer_norm2.weight": "model-00004-of-00004.safetensors",
614
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.bias": "model-00004-of-00004.safetensors",
615
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc1.weight": "model-00004-of-00004.safetensors",
616
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.bias": "model-00004-of-00004.safetensors",
617
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.mlp.fc2.weight": "model-00004-of-00004.safetensors",
618
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
619
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
620
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
621
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
622
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
623
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
624
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
625
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.17.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
626
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.bias": "model-00004-of-00004.safetensors",
627
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm1.weight": "model-00004-of-00004.safetensors",
628
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.bias": "model-00004-of-00004.safetensors",
629
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.layer_norm2.weight": "model-00004-of-00004.safetensors",
630
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.bias": "model-00004-of-00004.safetensors",
631
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc1.weight": "model-00004-of-00004.safetensors",
632
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.bias": "model-00004-of-00004.safetensors",
633
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.mlp.fc2.weight": "model-00004-of-00004.safetensors",
634
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
635
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
636
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
637
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
638
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
639
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
640
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
641
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.18.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
642
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.bias": "model-00004-of-00004.safetensors",
643
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm1.weight": "model-00004-of-00004.safetensors",
644
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.bias": "model-00004-of-00004.safetensors",
645
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.layer_norm2.weight": "model-00004-of-00004.safetensors",
646
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.bias": "model-00004-of-00004.safetensors",
647
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc1.weight": "model-00004-of-00004.safetensors",
648
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.bias": "model-00004-of-00004.safetensors",
649
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.mlp.fc2.weight": "model-00004-of-00004.safetensors",
650
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
651
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
652
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
653
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
654
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
655
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
656
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
657
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.19.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
658
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.bias": "model-00004-of-00004.safetensors",
659
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm1.weight": "model-00004-of-00004.safetensors",
660
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.bias": "model-00004-of-00004.safetensors",
661
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.layer_norm2.weight": "model-00004-of-00004.safetensors",
662
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.bias": "model-00004-of-00004.safetensors",
663
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc1.weight": "model-00004-of-00004.safetensors",
664
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.bias": "model-00004-of-00004.safetensors",
665
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.mlp.fc2.weight": "model-00004-of-00004.safetensors",
666
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
667
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
668
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
669
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
670
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
671
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
672
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
673
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.2.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
674
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.bias": "model-00004-of-00004.safetensors",
675
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm1.weight": "model-00004-of-00004.safetensors",
676
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.bias": "model-00004-of-00004.safetensors",
677
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.layer_norm2.weight": "model-00004-of-00004.safetensors",
678
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.bias": "model-00004-of-00004.safetensors",
679
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc1.weight": "model-00004-of-00004.safetensors",
680
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.bias": "model-00004-of-00004.safetensors",
681
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.mlp.fc2.weight": "model-00004-of-00004.safetensors",
682
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
683
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
684
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
685
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
686
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
687
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
688
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
689
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.20.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
690
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.bias": "model-00004-of-00004.safetensors",
691
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm1.weight": "model-00004-of-00004.safetensors",
692
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.bias": "model-00004-of-00004.safetensors",
693
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.layer_norm2.weight": "model-00004-of-00004.safetensors",
694
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.bias": "model-00004-of-00004.safetensors",
695
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc1.weight": "model-00004-of-00004.safetensors",
696
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.bias": "model-00004-of-00004.safetensors",
697
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.mlp.fc2.weight": "model-00004-of-00004.safetensors",
698
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
699
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
700
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
701
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
702
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
703
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
704
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
705
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.21.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
706
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.bias": "model-00004-of-00004.safetensors",
707
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm1.weight": "model-00004-of-00004.safetensors",
708
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.bias": "model-00004-of-00004.safetensors",
709
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.layer_norm2.weight": "model-00004-of-00004.safetensors",
710
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.bias": "model-00004-of-00004.safetensors",
711
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc1.weight": "model-00004-of-00004.safetensors",
712
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.bias": "model-00004-of-00004.safetensors",
713
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.mlp.fc2.weight": "model-00004-of-00004.safetensors",
714
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
715
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
716
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
717
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
718
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
719
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
720
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
721
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.22.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
722
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.bias": "model-00004-of-00004.safetensors",
723
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm1.weight": "model-00004-of-00004.safetensors",
724
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.bias": "model-00004-of-00004.safetensors",
725
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.layer_norm2.weight": "model-00004-of-00004.safetensors",
726
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.bias": "model-00004-of-00004.safetensors",
727
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc1.weight": "model-00004-of-00004.safetensors",
728
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.bias": "model-00004-of-00004.safetensors",
729
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.mlp.fc2.weight": "model-00004-of-00004.safetensors",
730
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
731
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
732
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
733
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
734
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
735
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
736
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
737
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.23.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
738
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.bias": "model-00004-of-00004.safetensors",
739
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm1.weight": "model-00004-of-00004.safetensors",
740
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.bias": "model-00004-of-00004.safetensors",
741
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.layer_norm2.weight": "model-00004-of-00004.safetensors",
742
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.bias": "model-00004-of-00004.safetensors",
743
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc1.weight": "model-00004-of-00004.safetensors",
744
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.bias": "model-00004-of-00004.safetensors",
745
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.mlp.fc2.weight": "model-00004-of-00004.safetensors",
746
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
747
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
748
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
749
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
750
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
751
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
752
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
753
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
754
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.bias": "model-00004-of-00004.safetensors",
755
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm1.weight": "model-00004-of-00004.safetensors",
756
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.bias": "model-00004-of-00004.safetensors",
757
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.layer_norm2.weight": "model-00004-of-00004.safetensors",
758
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.bias": "model-00004-of-00004.safetensors",
759
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc1.weight": "model-00004-of-00004.safetensors",
760
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.bias": "model-00004-of-00004.safetensors",
761
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.mlp.fc2.weight": "model-00004-of-00004.safetensors",
762
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
763
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
764
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
765
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
766
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
767
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
768
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
769
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.4.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
770
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.bias": "model-00004-of-00004.safetensors",
771
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm1.weight": "model-00004-of-00004.safetensors",
772
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.bias": "model-00004-of-00004.safetensors",
773
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.layer_norm2.weight": "model-00004-of-00004.safetensors",
774
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.bias": "model-00004-of-00004.safetensors",
775
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc1.weight": "model-00004-of-00004.safetensors",
776
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.bias": "model-00004-of-00004.safetensors",
777
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.mlp.fc2.weight": "model-00004-of-00004.safetensors",
778
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
779
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
780
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
781
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
782
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
783
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
784
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
785
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
786
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.bias": "model-00004-of-00004.safetensors",
787
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm1.weight": "model-00004-of-00004.safetensors",
788
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.bias": "model-00004-of-00004.safetensors",
789
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.layer_norm2.weight": "model-00004-of-00004.safetensors",
790
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.bias": "model-00004-of-00004.safetensors",
791
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc1.weight": "model-00004-of-00004.safetensors",
792
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.bias": "model-00004-of-00004.safetensors",
793
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.mlp.fc2.weight": "model-00004-of-00004.safetensors",
794
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
795
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
796
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
797
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
798
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
799
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
800
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
801
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.6.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
802
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.bias": "model-00004-of-00004.safetensors",
803
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm1.weight": "model-00004-of-00004.safetensors",
804
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.bias": "model-00004-of-00004.safetensors",
805
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.layer_norm2.weight": "model-00004-of-00004.safetensors",
806
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.bias": "model-00004-of-00004.safetensors",
807
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc1.weight": "model-00004-of-00004.safetensors",
808
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.bias": "model-00004-of-00004.safetensors",
809
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.mlp.fc2.weight": "model-00004-of-00004.safetensors",
810
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
811
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
812
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
813
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
814
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
815
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
816
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
817
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
818
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.bias": "model-00004-of-00004.safetensors",
819
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm1.weight": "model-00004-of-00004.safetensors",
820
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.bias": "model-00004-of-00004.safetensors",
821
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.layer_norm2.weight": "model-00004-of-00004.safetensors",
822
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.bias": "model-00004-of-00004.safetensors",
823
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc1.weight": "model-00004-of-00004.safetensors",
824
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.bias": "model-00004-of-00004.safetensors",
825
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.mlp.fc2.weight": "model-00004-of-00004.safetensors",
826
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
827
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
828
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
829
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
830
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
831
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
832
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
833
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
834
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.bias": "model-00004-of-00004.safetensors",
835
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm1.weight": "model-00004-of-00004.safetensors",
836
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.bias": "model-00004-of-00004.safetensors",
837
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.layer_norm2.weight": "model-00004-of-00004.safetensors",
838
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.bias": "model-00004-of-00004.safetensors",
839
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc1.weight": "model-00004-of-00004.safetensors",
840
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.bias": "model-00004-of-00004.safetensors",
841
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.mlp.fc2.weight": "model-00004-of-00004.safetensors",
842
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.bias": "model-00004-of-00004.safetensors",
843
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
844
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
845
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
846
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.bias": "model-00004-of-00004.safetensors",
847
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
848
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.bias": "model-00004-of-00004.safetensors",
849
+ "model.vision_tower.vision_tower.vision_model.encoder.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
850
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.bias": "model-00004-of-00004.safetensors",
851
+ "model.vision_tower.vision_tower.vision_model.post_layernorm.weight": "model-00004-of-00004.safetensors",
852
+ "model.vision_tower.vision_tower.vision_model.pre_layrnorm.bias": "model-00004-of-00004.safetensors",
853
+ "model.vision_tower.vision_tower.vision_model.pre_layrnorm.weight": "model-00004-of-00004.safetensors"
854
+ }
855
+ }
modeling_360vl.py ADDED
@@ -0,0 +1,809 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from typing import List, Optional, Tuple, Union
2
+
3
+ import torch
4
+ import torch.nn as nn
5
+
6
+ from torch.nn import CrossEntropyLoss
7
+
8
+ from transformers import AutoConfig, AutoModelForCausalLM, \
9
+ LlamaConfig, LlamaModel, LlamaForCausalLM
10
+
11
+ from transformers.modeling_outputs import CausalLMOutputWithPast
12
+
13
+ from PIL import Image
14
+
15
+ from abc import ABC, abstractmethod
16
+ import os
17
+
18
+ import math
19
+ from transformers import CLIPVisionModel, CLIPImageProcessor, CLIPVisionConfig
20
+ from functools import partial
21
+ from transformers.configuration_utils import PretrainedConfig
22
+
23
+ from timm.models.layers import LayerNorm, LayerNorm2d
24
+ from timm.models.regnet import RegStage
25
+ from torch.nn import functional as F
26
+ import math
27
+ from einops import rearrange
28
+
29
+
30
+
31
+ CONTROLLER_HEART_BEAT_EXPIRATION = 30
32
+ WORKER_HEART_BEAT_INTERVAL = 15
33
+
34
+ LOGDIR = "."
35
+
36
+ # Model Constants
37
+ IGNORE_INDEX = -100
38
+ IMAGE_TOKEN_INDEX = -200
39
+ DEFAULT_IMAGE_TOKEN = "<image>"
40
+ DEFAULT_IMAGE_PATCH_TOKEN = "<im_patch>"
41
+ DEFAULT_IM_START_TOKEN = "<im_start>"
42
+ DEFAULT_IM_END_TOKEN = "<im_end>"
43
+
44
+
45
+
46
+
47
+
48
+ class CLIPVisionTower(nn.Module):
49
+ def __init__(self, vision_tower, args, delay_load=False):
50
+ super().__init__()
51
+
52
+ self.is_loaded = False
53
+
54
+ self.vision_tower_name = vision_tower
55
+ self.select_layer = args.mm_vision_select_layer
56
+ self.select_feature = getattr(args, 'mm_vision_select_feature', 'patch')
57
+
58
+ if not delay_load:
59
+ self.load_model()
60
+ else:
61
+ self.cfg_only = CLIPVisionConfig.from_pretrained(self.vision_tower_name)
62
+
63
+ def load_model(self):
64
+ self.image_processor = CLIPImageProcessor.from_pretrained(self.vision_tower_name)
65
+ self.vision_tower = CLIPVisionModel.from_pretrained(self.vision_tower_name)
66
+ self.vision_tower.requires_grad_(False)
67
+
68
+ self.is_loaded = True
69
+
70
+ def feature_select(self, image_forward_outs):
71
+ image_features = image_forward_outs.hidden_states[self.select_layer]
72
+ if self.select_feature == 'patch':
73
+ image_features = image_features[:, 1:]
74
+ elif self.select_feature == 'cls_patch':
75
+ image_features = image_features
76
+ else:
77
+ raise ValueError(f'Unexpected select feature: {self.select_feature}')
78
+ return image_features
79
+
80
+ @torch.no_grad()
81
+ def forward(self, images):
82
+ if type(images) is list:
83
+ image_features = []
84
+ for image in images:
85
+ image_forward_out = self.vision_tower(image.to(device=self.device, dtype=self.dtype).unsqueeze(0), output_hidden_states=True)
86
+ image_feature = self.feature_select(image_forward_out).to(image.dtype)
87
+ image_features.append(image_feature)
88
+ else:
89
+ image_forward_outs = self.vision_tower(images.to(device=self.device, dtype=self.dtype), output_hidden_states=True)
90
+ image_features = self.feature_select(image_forward_outs).to(images.dtype)
91
+
92
+ return image_features
93
+
94
+ @property
95
+ def dummy_feature(self):
96
+ return torch.zeros(1, self.hidden_size, device=self.device, dtype=self.dtype)
97
+
98
+ @property
99
+ def dtype(self):
100
+ return self.vision_tower.dtype
101
+
102
+ @property
103
+ def device(self):
104
+ return self.vision_tower.device
105
+
106
+ @property
107
+ def config(self):
108
+ if self.is_loaded:
109
+ return self.vision_tower.config
110
+ else:
111
+ return self.cfg_only
112
+
113
+ @property
114
+ def hidden_size(self):
115
+ return self.config.hidden_size
116
+
117
+ @property
118
+ def num_patches(self):
119
+ return (self.config.image_size // self.config.patch_size) ** 2
120
+
121
+
122
+ def build_vision_tower(vision_tower_cfg, **kwargs):
123
+ vision_tower = getattr(vision_tower_cfg, 'mm_vision_tower', getattr(vision_tower_cfg, 'vision_tower', None))
124
+ is_absolute_path_exists = os.path.exists(vision_tower)
125
+
126
+ if is_absolute_path_exists or vision_tower.startswith("openai") or vision_tower.startswith("laion"):
127
+ return CLIPVisionTower(vision_tower, args=vision_tower_cfg, **kwargs)
128
+
129
+ raise ValueError(f'Unknown vision tower: {vision_tower}')
130
+
131
+
132
+
133
+
134
+
135
+ class HoneybeeVisualProjectorConfig(PretrainedConfig):
136
+ model_type = "mllm_visual_projector"
137
+
138
+ def __init__(
139
+ self,
140
+ projector_type: str = "resampler",
141
+ hidden_size: int = 1024, #
142
+ num_hidden_layers: int = 6, #
143
+ num_attention_heads: int = 16, #
144
+ intermediate_size: int = 4096, #
145
+ attention_probs_dropout_prob: float = 0.1, #
146
+ initializer_range: float = 0.02,
147
+ layer_norm_eps: float = 1e-6, #
148
+ encoder_hidden_size: int = 1024, # This will be overwritten by vision_model's hidden_size
149
+ pos_emb=False,
150
+ feature_layer_index=-1, # vision feature layer index; -1: last layer
151
+ num_eos_tokens=1,
152
+ use_cls=True,
153
+ prenorm=False,
154
+ **kwargs,
155
+ ):
156
+ super().__init__(**kwargs)
157
+ self.projector_type = projector_type
158
+ self.hidden_size = hidden_size
159
+ self.num_hidden_layers = num_hidden_layers
160
+ self.num_attention_heads = num_attention_heads
161
+ self.intermediate_size = intermediate_size
162
+ self.attention_probs_dropout_prob = attention_probs_dropout_prob
163
+ self.initializer_range = initializer_range
164
+ self.layer_norm_eps = layer_norm_eps
165
+ self.encoder_hidden_size = encoder_hidden_size
166
+
167
+ self.pos_emb = pos_emb
168
+ self.feature_layer_index = feature_layer_index
169
+ self.num_eos_tokens = num_eos_tokens
170
+ self.use_cls = use_cls
171
+ self.prenorm = prenorm
172
+
173
+ @classmethod
174
+ def from_pretrained(
175
+ cls, pretrained_model_name_or_path: Union[str, os.PathLike], **kwargs
176
+ ) -> "PretrainedConfig":
177
+ config_dict, kwargs = cls.get_config_dict(pretrained_model_name_or_path, **kwargs)
178
+
179
+ # get the visual_projector config dict if we are loading from HoneybeeConfig
180
+ if config_dict.get("model_type") == "mllm":
181
+ config_dict = config_dict["visual_projector_config"]
182
+
183
+ if (
184
+ "model_type" in config_dict
185
+ and hasattr(cls, "model_type")
186
+ and config_dict["model_type"] != cls.model_type
187
+ ):
188
+ logger.warning(
189
+ f"You are using a model of type {config_dict['model_type']} to instantiate a model of type "
190
+ f"{cls.model_type}. This is not supported for all configurations of models and can yield errors."
191
+ )
192
+
193
+ return cls.from_dict(config_dict, **kwargs)
194
+
195
+ def build_pos_embeds(
196
+ config: HoneybeeVisualProjectorConfig, num_input_tokens: int, vision_hidden_size: int
197
+ ):
198
+ # pos emb
199
+ # true
200
+ if config.pos_emb:
201
+ pos_emb = torch.nn.Parameter(torch.zeros(1, num_input_tokens, vision_hidden_size))
202
+ nn.init.trunc_normal_(pos_emb, mean=0.0, std=0.02)
203
+ else:
204
+ pos_emb = None
205
+
206
+ return pos_emb
207
+
208
+
209
+ def build_eos_tokens(config: HoneybeeVisualProjectorConfig, output_hidden_size: int):
210
+ # think tokens
211
+ num_eos_tokens = config.num_eos_tokens
212
+ # 0
213
+ if num_eos_tokens:
214
+ eos_tokens = torch.nn.Parameter(torch.randn(1, num_eos_tokens, output_hidden_size))
215
+ nn.init.trunc_normal_(eos_tokens, mean=0.0, std=config.initializer_range)
216
+ else:
217
+ eos_tokens = None
218
+
219
+ return eos_tokens
220
+
221
+
222
+ def build_prenorm(config: HoneybeeVisualProjectorConfig):
223
+ # false
224
+ if config.prenorm:
225
+ prenorm = LayerNorm(config.encoder_hidden_size)
226
+ else:
227
+ prenorm = None
228
+ return prenorm
229
+
230
+
231
+ def build_mlp(depth, hidden_size, output_hidden_size):
232
+ layers = [nn.Linear(hidden_size, output_hidden_size)]
233
+ for _ in range(1, depth):
234
+ layers.append(nn.SiLU())
235
+ layers.append(nn.Linear(output_hidden_size, output_hidden_size))
236
+ return nn.Sequential(*layers)
237
+
238
+ def get_abs_pos(abs_pos, tgt_size):
239
+ # abs_pos: L, C
240
+ # tgt_size: M
241
+ # return: M, C
242
+ # 16,24
243
+ src_size = int(math.sqrt(abs_pos.size(1)))
244
+ # 32,48
245
+ tgt_size = int(math.sqrt(tgt_size))
246
+ dtype = abs_pos.dtype
247
+
248
+ if src_size != tgt_size:
249
+ return F.interpolate(
250
+ abs_pos.float().reshape(1, src_size, src_size, -1).permute(0, 3, 1, 2),
251
+ size=(tgt_size, tgt_size),
252
+ mode="bicubic",
253
+ align_corners=False,
254
+ ).permute(0, 2, 3, 1).flatten(0, 2).to(dtype=dtype)
255
+ else:
256
+ return abs_pos
257
+
258
+
259
+ class Projector(nn.Module):
260
+ """Base projector class"""
261
+
262
+ def __init__(
263
+ self,
264
+ config: HoneybeeVisualProjectorConfig,
265
+ num_input_tokens: int,
266
+ output_hidden_size: int,
267
+ ):
268
+ super().__init__()
269
+ self.config = config
270
+ self.num_input_tokens = num_input_tokens
271
+ self.output_hidden_size = output_hidden_size
272
+
273
+ # think tokens
274
+ self.eos_tokens = build_eos_tokens(config, output_hidden_size)
275
+
276
+ # pos emb
277
+ self.pos_emb = build_pos_embeds(config, num_input_tokens, config.encoder_hidden_size)
278
+
279
+ self.prenorm = build_prenorm(config)
280
+
281
+ self.build_net()
282
+
283
+ def build_net(self):
284
+ raise NotImplementedError()
285
+
286
+ def _forward(self, x):
287
+ raise NotImplementedError()
288
+
289
+ def forward(self, x: torch.Tensor) -> torch.Tensor:
290
+ """
291
+ Args:
292
+ x: (B, L, encoder_hidden_size) tensor from the visual backbone (CLIP visual encoder), including cls token.
293
+ """
294
+ if self.prenorm is not None:
295
+ x = self.prenorm(x)
296
+
297
+ if self.pos_emb is not None:
298
+ # self.pos_emb = self.pos_emb[:,1:]
299
+ pos_emb = get_abs_pos(self.pos_emb[:,1:], x.size(1))
300
+ pos_emb = pos_emb.to(device=x.device)
301
+ x += pos_emb
302
+
303
+ x = self._forward(x) # (B, L, output_hidden_size)
304
+
305
+ B = x.size(0)
306
+ if self.eos_tokens is not None:
307
+ x = torch.cat([x, self.eos_tokens.expand(B, -1, -1)], dim=1)
308
+ return x
309
+
310
+
311
+ class ConvProjector(Projector):
312
+ def _forward(self, x):
313
+ # x: [B, L, dim]
314
+ # x = x[:, 1:] # drop cls token and 2d forward
315
+
316
+ hw = int(x.size(1) ** 0.5)
317
+ x = rearrange(x, "b (h w) d -> b d h w", h=hw, w=hw)
318
+ x = self.net(x)
319
+ x = rearrange(x, "b d h w -> b (h w) d")
320
+ x = self.readout(x)
321
+
322
+ return x
323
+
324
+
325
+ class CAbstractor(ConvProjector):
326
+ """C-Abstractor"""
327
+ def build_net(self):
328
+ encoder_hidden_size = self.config.encoder_hidden_size
329
+ hidden_size = self.config.hidden_size
330
+ output_hidden_size = self.output_hidden_size
331
+ depth = self.config.depth
332
+ mlp_depth = self.config.mlp_depth
333
+
334
+ n_queries = self.config.num_queries
335
+ assert (n_queries ** 0.5).is_integer(), "n_queries must be square number"
336
+ hw = int(n_queries ** 0.5)
337
+
338
+ # RegBlock = ResBlock + SE
339
+ RegBlock = partial(
340
+ RegStage,
341
+ stride=1,
342
+ dilation=1,
343
+ act_layer=nn.SiLU,
344
+ norm_layer=LayerNorm2d,
345
+ )
346
+
347
+ s1 = RegBlock(
348
+ depth,
349
+ encoder_hidden_size,
350
+ hidden_size,
351
+ )
352
+ sampler = nn.AdaptiveAvgPool2d((hw, hw))
353
+ s2 = RegBlock(
354
+ depth,
355
+ hidden_size,
356
+ hidden_size,
357
+ )
358
+
359
+ self.net = nn.Sequential(s1, sampler, s2)
360
+ self.readout = build_mlp(mlp_depth, hidden_size, output_hidden_size)
361
+
362
+ class IdentityMap(nn.Module):
363
+ def __init__(self):
364
+ super().__init__()
365
+
366
+ def forward(self, x, *args, **kwargs):
367
+ return x
368
+
369
+ @property
370
+ def config(self):
371
+ return {"mm_projector_type": 'identity'}
372
+
373
+
374
+ class SimpleResBlock(nn.Module):
375
+ def __init__(self, channels):
376
+ super().__init__()
377
+ self.pre_norm = nn.LayerNorm(channels)
378
+
379
+ self.proj = nn.Sequential(
380
+ nn.Linear(channels, channels),
381
+ nn.GELU(),
382
+ nn.Linear(channels, channels)
383
+ )
384
+ def forward(self, x):
385
+ x = self.pre_norm(x)
386
+ return x + self.proj(x)
387
+
388
+
389
+ def build_honeybee_projector(config, projector_type, num_tokens,lm_hidden_size):
390
+ """Build projector (abstractor) and query_tokens (optionally for resampler)"""
391
+ proj_config = config
392
+ proj_type = projector_type
393
+ num_tokens = num_tokens
394
+ output_hidden_size = lm_hidden_size # LM hidden size
395
+
396
+ abstractor = {
397
+ "c-abs": CAbstractor,
398
+ }[
399
+ proj_type
400
+ ](proj_config, num_tokens, output_hidden_size)
401
+ return abstractor
402
+
403
+
404
+ def build_vision_projector(config, delay_load=False, **kwargs):
405
+ projector_type = getattr(config, 'mm_projector_type', 'linear')
406
+
407
+ if projector_type == 'linear':
408
+ return nn.Linear(config.mm_hidden_size, config.hidden_size)
409
+
410
+ if projector_type == 'c-abs':
411
+
412
+ local_config_path = config.mm_projector_config
413
+ honeybee_config = HoneybeeVisualProjectorConfig.from_pretrained(local_config_path)
414
+
415
+ num_tokens = config.mm_num_tokens
416
+
417
+ lm_hidden_size = config.hidden_size
418
+
419
+ abstractor = build_honeybee_projector(honeybee_config,projector_type,num_tokens,lm_hidden_size)
420
+ return abstractor
421
+
422
+ mlp_gelu_match = re.match(r'^mlp(\d+)x_gelu$', projector_type)
423
+ if mlp_gelu_match:
424
+ mlp_depth = int(mlp_gelu_match.group(1))
425
+ modules = [nn.Linear(config.mm_hidden_size, config.hidden_size)]
426
+ for _ in range(1, mlp_depth):
427
+ modules.append(nn.GELU())
428
+ modules.append(nn.Linear(config.hidden_size, config.hidden_size))
429
+ return nn.Sequential(*modules)
430
+
431
+ if projector_type == 'identity':
432
+ return IdentityMap()
433
+
434
+ raise ValueError(f'Unknown projector type: {projector_type}')
435
+
436
+
437
+
438
+
439
+ class QH360_VL_MetaModel:
440
+
441
+ def __init__(self, config):
442
+ super(QH360_VL_MetaModel, self).__init__(config)
443
+ if hasattr(config, "mm_vision_tower"):
444
+ self.vision_tower = build_vision_tower(config, delay_load=True)
445
+ self.mm_projector_ctt = build_vision_projector(config)
446
+ self.mm_projector_ori = build_vision_projector(config)
447
+
448
+
449
+
450
+ def get_vision_tower(self):
451
+ vision_tower = getattr(self, 'vision_tower', None)
452
+ if type(vision_tower) is list:
453
+ vision_tower = vision_tower[0]
454
+ return vision_tower
455
+
456
+
457
+ class QH360_VL_MetaForCausalLM(ABC):
458
+
459
+ @abstractmethod
460
+ def get_model(self):
461
+ pass
462
+
463
+ def get_vision_tower(self):
464
+ return self.get_model().get_vision_tower()
465
+
466
+ def encode_images(self, images):
467
+ image_features = self.get_model().get_vision_tower()(images)
468
+ image_features = self.get_model().mm_projector(image_features)
469
+ return image_features
470
+
471
+ def encode_images_noprojector(self, images):
472
+ image_features = self.get_model().get_vision_tower()(images)
473
+ image_features = image_features.detach()
474
+ return image_features
475
+
476
+ def prepare_inputs_labels_for_multimodal(
477
+ self, input_ids, attention_mask, past_key_values, labels, images
478
+ ):
479
+ vision_tower = self.get_vision_tower()
480
+ if vision_tower is None or images is None or input_ids.shape[1] == 1:
481
+ if past_key_values is not None and vision_tower is not None and images is not None and input_ids.shape[1] == 1:
482
+ attention_mask = torch.ones((attention_mask.shape[0], past_key_values[-1][-1].shape[-2] + 1), dtype=attention_mask.dtype, device=attention_mask.device)
483
+ return input_ids, attention_mask, past_key_values, None, labels
484
+
485
+ if type(images) is list or images.ndim == 5:
486
+ image_features = []
487
+ for image in images:
488
+ if image.ndim == 3:
489
+ image_features.append(self.encode_images(image.unsqueeze(0)).squeeze(0))
490
+ elif image.ndim == 4:
491
+ #NOTE cc-plan
492
+ temp_feats = self.encode_images_noprojector(image)
493
+ src_size = int(math.sqrt(temp_feats.shape[1]))
494
+ temp_feats = temp_feats.reshape(temp_feats.shape[0]//5,5,-1, temp_feats.shape[-1])
495
+ x1 = temp_feats[:,4,:,:]
496
+ x = temp_feats[:,:4,:,:]
497
+ x = x.reshape(x.shape[0], -1, src_size, src_size, x.shape[-1])
498
+ x = x.transpose(1,2).reshape(x.shape[0], src_size,2,2, src_size, x.shape[-1])
499
+ x = x.transpose(1,2).reshape(x.shape[0], -1, x.shape[-1])
500
+ x1 = self.get_model().mm_projector_ori(x1).squeeze(0)
501
+ x = self.get_model().mm_projector_ctt(x).squeeze(0)
502
+ temp_feats_all = torch.cat([x,x1],dim=0)
503
+ image_features.append(temp_feats_all)
504
+ else:
505
+ image_features = self.encode_images(images)
506
+
507
+
508
+ new_input_embeds = []
509
+ new_labels = [] if labels is not None else None
510
+ cur_image_idx = 0
511
+ for batch_idx, cur_input_ids in enumerate(input_ids):
512
+ if (cur_input_ids == IMAGE_TOKEN_INDEX).sum() == 0:
513
+ # multimodal LLM, but the current sample is not multimodal
514
+ # FIXME: this is a hacky fix, for deepspeed zero3 to work
515
+ half_len = cur_input_ids.shape[0] // 2
516
+ cur_image_features = image_features[cur_image_idx]
517
+ cur_input_embeds_1 = self.get_model().embed_tokens(cur_input_ids[:half_len])
518
+ cur_input_embeds_2 = self.get_model().embed_tokens(cur_input_ids[half_len:])
519
+ cur_input_embeds = torch.cat([cur_input_embeds_1, cur_image_features[0:0], cur_input_embeds_2], dim=0)
520
+ new_input_embeds.append(cur_input_embeds)
521
+ if labels is not None:
522
+ new_labels.append(labels[batch_idx])
523
+ cur_image_idx += 1
524
+ continue
525
+ image_token_indices = torch.where(cur_input_ids == IMAGE_TOKEN_INDEX)[0]
526
+ cur_new_input_embeds = []
527
+ if labels is not None:
528
+ cur_labels = labels[batch_idx]
529
+ cur_new_labels = []
530
+ assert cur_labels.shape == cur_input_ids.shape
531
+ while image_token_indices.numel() > 0:
532
+ cur_image_features = image_features[cur_image_idx]
533
+ image_token_start = image_token_indices[0]
534
+ if getattr(self.config, 'tune_mm_mlp_adapter', False) and getattr(self.config, 'mm_use_im_start_end', False):
535
+ cur_new_input_embeds.append(self.get_model().embed_tokens(cur_input_ids[:image_token_start-1]).detach())
536
+ cur_new_input_embeds.append(self.get_model().embed_tokens(cur_input_ids[image_token_start-1:image_token_start]))
537
+ cur_new_input_embeds.append(cur_image_features)
538
+ cur_new_input_embeds.append(self.get_model().embed_tokens(cur_input_ids[image_token_start+1:image_token_start+2]))
539
+ if labels is not None:
540
+ cur_new_labels.append(cur_labels[:image_token_start])
541
+ cur_new_labels.append(torch.full((cur_image_features.shape[0],), IGNORE_INDEX, device=labels.device, dtype=labels.dtype))
542
+ cur_new_labels.append(cur_labels[image_token_start:image_token_start+1])
543
+ cur_labels = cur_labels[image_token_start+2:]
544
+ else:
545
+ cur_new_input_embeds.append(self.get_model().embed_tokens(cur_input_ids[:image_token_start]))
546
+ cur_new_input_embeds.append(cur_image_features)
547
+ if labels is not None:
548
+ cur_new_labels.append(cur_labels[:image_token_start])
549
+ cur_new_labels.append(torch.full((cur_image_features.shape[0],), IGNORE_INDEX, device=labels.device, dtype=labels.dtype))
550
+ cur_labels = cur_labels[image_token_start+1:]
551
+ cur_image_idx += 1
552
+ if getattr(self.config, 'tune_mm_mlp_adapter', False) and getattr(self.config, 'mm_use_im_start_end', False):
553
+ cur_input_ids = cur_input_ids[image_token_start+2:]
554
+ else:
555
+ cur_input_ids = cur_input_ids[image_token_start+1:]
556
+ image_token_indices = torch.where(cur_input_ids == IMAGE_TOKEN_INDEX)[0]
557
+ if cur_input_ids.numel() > 0:
558
+ if getattr(self.config, 'tune_mm_mlp_adapter', False) and getattr(self.config, 'mm_use_im_start_end', False):
559
+ cur_new_input_embeds.append(self.get_model().embed_tokens(cur_input_ids).detach())
560
+ else:
561
+ cur_new_input_embeds.append(self.get_model().embed_tokens(cur_input_ids))
562
+ if labels is not None:
563
+ cur_new_labels.append(cur_labels)
564
+ cur_new_input_embeds = [x.to(device=self.device) for x in cur_new_input_embeds]
565
+ cur_new_input_embeds = torch.cat(cur_new_input_embeds, dim=0)
566
+ new_input_embeds.append(cur_new_input_embeds)
567
+ if labels is not None:
568
+ cur_new_labels = torch.cat(cur_new_labels, dim=0)
569
+ new_labels.append(cur_new_labels)
570
+
571
+ if any(x.shape != new_input_embeds[0].shape for x in new_input_embeds):
572
+ max_len = max(x.shape[0] for x in new_input_embeds)
573
+
574
+ new_input_embeds_align = []
575
+ for cur_new_embed in new_input_embeds:
576
+ cur_new_embed = torch.cat((cur_new_embed, torch.zeros((max_len - cur_new_embed.shape[0], cur_new_embed.shape[1]), dtype=cur_new_embed.dtype, device=cur_new_embed.device)), dim=0)
577
+ new_input_embeds_align.append(cur_new_embed)
578
+ new_input_embeds = torch.stack(new_input_embeds_align, dim=0)
579
+
580
+ if labels is not None:
581
+ new_labels_align = []
582
+ _new_labels = new_labels
583
+ for cur_new_label in new_labels:
584
+ cur_new_label = torch.cat((cur_new_label, torch.full((max_len - cur_new_label.shape[0],), IGNORE_INDEX, dtype=cur_new_label.dtype, device=cur_new_label.device)), dim=0)
585
+ new_labels_align.append(cur_new_label)
586
+ new_labels = torch.stack(new_labels_align, dim=0)
587
+
588
+ if attention_mask is not None:
589
+ new_attention_mask = []
590
+ for cur_attention_mask, cur_new_labels, cur_new_labels_align in zip(attention_mask, _new_labels, new_labels):
591
+ new_attn_mask_pad_left = torch.full((cur_new_labels.shape[0] - labels.shape[1],), True, dtype=attention_mask.dtype, device=attention_mask.device)
592
+ new_attn_mask_pad_right = torch.full((cur_new_labels_align.shape[0] - cur_new_labels.shape[0],), False, dtype=attention_mask.dtype, device=attention_mask.device)
593
+ cur_new_attention_mask = torch.cat((new_attn_mask_pad_left, cur_attention_mask, new_attn_mask_pad_right), dim=0)
594
+ new_attention_mask.append(cur_new_attention_mask)
595
+ attention_mask = torch.stack(new_attention_mask, dim=0)
596
+ assert attention_mask.shape == new_labels.shape
597
+ else:
598
+ new_input_embeds = torch.stack(new_input_embeds, dim=0)
599
+ if labels is not None:
600
+ new_labels = torch.stack(new_labels, dim=0)
601
+
602
+ if attention_mask is not None:
603
+ new_attn_mask_pad_left = torch.full((attention_mask.shape[0], new_input_embeds.shape[1] - input_ids.shape[1]), True, dtype=attention_mask.dtype, device=attention_mask.device)
604
+ attention_mask = torch.cat((new_attn_mask_pad_left, attention_mask), dim=1)
605
+ assert attention_mask.shape == new_input_embeds.shape[:2]
606
+
607
+ return None, attention_mask, past_key_values, new_input_embeds, new_labels
608
+
609
+
610
+
611
+ class QH360_VLConfig(LlamaConfig):
612
+ model_type = "QH_360VL"
613
+
614
+
615
+ class QH360_VL_LlamaModel(QH360_VL_MetaModel, LlamaModel):
616
+ config_class = QH360_VLConfig
617
+
618
+ def __init__(self, config: LlamaConfig):
619
+ super(QH360_VL_LlamaModel, self).__init__(config)
620
+
621
+
622
+ class QH360_VL_LlamaForCausalLM(LlamaForCausalLM, QH360_VL_MetaForCausalLM):
623
+ config_class = QH360_VLConfig
624
+
625
+ def __init__(self, config):
626
+ super(LlamaForCausalLM, self).__init__(config)
627
+ config._attn_implementation == "flash_attention_2"
628
+ self.model = QH360_VL_LlamaModel(config)
629
+
630
+ self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
631
+
632
+ # Initialize weights and apply final processing
633
+ self.post_init()
634
+
635
+ def get_model(self):
636
+ return self.model
637
+
638
+ def forward(
639
+ self,
640
+ input_ids: torch.LongTensor = None,
641
+ attention_mask: Optional[torch.Tensor] = None,
642
+ past_key_values: Optional[List[torch.FloatTensor]] = None,
643
+ inputs_embeds: Optional[torch.FloatTensor] = None,
644
+ labels: Optional[torch.LongTensor] = None,
645
+ use_cache: Optional[bool] = None,
646
+ output_attentions: Optional[bool] = None,
647
+ output_hidden_states: Optional[bool] = None,
648
+ images: Optional[torch.FloatTensor] = None,
649
+ return_dict: Optional[bool] = None,
650
+ ) -> Union[Tuple, CausalLMOutputWithPast]:
651
+ output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
652
+ output_hidden_states = (
653
+ output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
654
+ )
655
+ return_dict = return_dict if return_dict is not None else self.config.use_return_dict
656
+
657
+ input_ids, attention_mask, past_key_values, inputs_embeds, labels = self.prepare_inputs_labels_for_multimodal(input_ids, attention_mask, past_key_values, labels, images)
658
+
659
+ # decoder outputs consists of (dec_features, layer_state, dec_hidden, dec_attn)
660
+ outputs = self.model(
661
+ input_ids=input_ids,
662
+ attention_mask=attention_mask,
663
+ past_key_values=past_key_values,
664
+ inputs_embeds=inputs_embeds,
665
+ use_cache=use_cache,
666
+ output_attentions=output_attentions,
667
+ output_hidden_states=output_hidden_states,
668
+ return_dict=return_dict
669
+ )
670
+
671
+ hidden_states = outputs[0]
672
+ logits = self.lm_head(hidden_states)
673
+
674
+ loss = None
675
+ if labels is not None:
676
+ # Shift so that tokens < n predict n
677
+ shift_logits = logits[..., :-1, :].contiguous()
678
+ shift_labels = labels[..., 1:].contiguous()
679
+ # Flatten the tokens
680
+ loss_fct = CrossEntropyLoss()
681
+ shift_logits = shift_logits.view(-1, self.config.vocab_size)
682
+ shift_labels = shift_labels.view(-1)
683
+ # Enable model/pipeline parallelism
684
+ shift_labels = shift_labels.to(shift_logits.device)
685
+ loss = loss_fct(shift_logits, shift_labels)
686
+
687
+ if not return_dict:
688
+ output = (logits,) + outputs[1:]
689
+ return (loss,) + output if loss is not None else output
690
+
691
+ return CausalLMOutputWithPast(
692
+ loss=loss,
693
+ logits=logits,
694
+ past_key_values=outputs.past_key_values,
695
+ hidden_states=outputs.hidden_states,
696
+ attentions=outputs.attentions,
697
+ )
698
+
699
+ def prepare_inputs_for_generation(
700
+ self, input_ids, past_key_values=None, attention_mask=None, inputs_embeds=None, **kwargs
701
+ ):
702
+ if past_key_values:
703
+ input_ids = input_ids[:, -1:]
704
+
705
+ # if `inputs_embeds` are passed, we only want to use them in the 1st generation step
706
+ if inputs_embeds is not None and past_key_values is None:
707
+ model_inputs = {"inputs_embeds": inputs_embeds}
708
+ else:
709
+ model_inputs = {"input_ids": input_ids}
710
+
711
+ model_inputs.update(
712
+ {
713
+ "past_key_values": past_key_values,
714
+ "use_cache": kwargs.get("use_cache"),
715
+ "attention_mask": attention_mask,
716
+ "images": kwargs.get("images", None),
717
+ }
718
+ )
719
+ return model_inputs
720
+
721
+ def build_conversation_input_ids(
722
+ self,
723
+ tokenizer: "PreTrainedTokenizer",
724
+ query: str,
725
+ image = None,
726
+ image_processor=None,
727
+ ):
728
+
729
+ input_msg = [
730
+ {
731
+ "role": "system",
732
+ "content": "You are a multilingual, helpful, respectful and honest assistant who can respond in the same language, depending on the language of the question. Try to be as helpful as possible while still being safe. Your answer should not contain anything that is false, unhealthy, harmful, immoral, racist, sexist, toxic, dangerous, or illegal, and if the question relates to such content, please decline to answer. Make sure your answer is socially fair and positive. If a question doesn't make any sense, or is inconsistent with the facts, explain why instead of answering the wrong answer. If you don't know the answer to a question, don't share false information."
733
+ },
734
+ {
735
+ "role": "user",
736
+ "content": "<|reserved_special_token_44|>"+ '\n' + query
737
+ }
738
+ ]
739
+
740
+ input_ids = tokenizer.apply_chat_template(
741
+ input_msg,
742
+ add_generation_prompt=True,
743
+ padding="longest",
744
+ return_tensors="pt",
745
+ )
746
+ input_id_list = input_ids[0].tolist()
747
+ input_id_list[input_id_list.index(128049)]=-200
748
+ input_ids = torch.tensor(input_id_list, dtype=input_ids.dtype,device=input_ids.device)
749
+ input_ids = input_ids.unsqueeze(0)
750
+ image_tensor = self.process_images_slid_window(image,image_processor).unsqueeze(0)
751
+
752
+ return {
753
+ 'input_ids': input_ids,
754
+ 'image': image_tensor,
755
+ }
756
+
757
+
758
+
759
+ def process_images_slid_window(self, image, image_processor, vit_is=336):
760
+
761
+ def get_proper_imgsize(pil_img, vit_is):
762
+ max_w_h = vit_is * 2
763
+ new_pil_img = pil_img.resize((max_w_h, max_w_h))
764
+ return new_pil_img
765
+
766
+ def tensor_crop(tensor_array, left, upper, right, lower):
767
+ # tensor_array: C * H * W
768
+ return tensor_array[:, upper:lower, left:right]
769
+
770
+ def image_slid_window(image, num_slid_window):
771
+ # image: tensor, 3 * 336 * 336 or 3 * 672 * 672
772
+ # image: tensor, 3 * 224 * 224 or 3 * 448 * 448
773
+ if num_slid_window == 5:
774
+ image_x2, image_x1 = image[0], image[1]
775
+ vit_is = image_x1.shape[1]
776
+ h, w = image_x2.shape[1],image_x2.shape[2]
777
+ image0 = tensor_crop(image_x2, 0, 0, vit_is, vit_is)
778
+ image1 = tensor_crop(image_x2, w-vit_is, 0, w, vit_is)
779
+ image2 = tensor_crop(image_x2, 0, h-vit_is, vit_is, h)
780
+ image3 = tensor_crop(image_x2, w-vit_is, h-vit_is, w, h)
781
+ return torch.stack([image0, image1, image2, image3, image_x1])
782
+ else:
783
+ return image
784
+
785
+ def expand2square(pil_img, background_color):
786
+ width, height = pil_img.size
787
+ if width == height:
788
+ return pil_img
789
+ elif width > height:
790
+ result = Image.new(pil_img.mode, (width, width), background_color)
791
+ result.paste(pil_img, (0, (width - height) // 2))
792
+ return result
793
+ else:
794
+ result = Image.new(pil_img.mode, (height, height), background_color)
795
+ result.paste(pil_img, ((height - width) // 2, 0))
796
+ return result
797
+
798
+ vit_is = vit_is # vit_input_size, for simplicity
799
+
800
+ num_slid_window = 5
801
+
802
+ image = expand2square(image, tuple(int(x*255) for x in image_processor.image_mean))
803
+ image = get_proper_imgsize(image, vit_is)
804
+ image_x2 = image_processor.preprocess(image, return_tensors='pt', do_resize=False, do_center_crop=False)['pixel_values'][0]
805
+ image_x1 = image_processor.preprocess(image, return_tensors='pt')['pixel_values'][0]
806
+ image = [image_x2, image_x1]
807
+ image = image_slid_window(image, num_slid_window)
808
+
809
+ return image
proj_config.json ADDED
@@ -0,0 +1,337 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "",
4
+ "architectures": [
5
+ "HoneybeeForConditionalGeneration"
6
+ ],
7
+ "hidden_act": "silu",
8
+ "hidden_size": 5120,
9
+ "initializer_factor": 1.0,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 13824,
12
+ "keys_to_ignore_at_inference": [
13
+ "past_key_values"
14
+ ],
15
+ "lm_config": {
16
+ "_name_or_path": "",
17
+ "add_cross_attention": false,
18
+ "architectures": null,
19
+ "bad_words_ids": null,
20
+ "begin_suppress_tokens": null,
21
+ "bos_token_id": null,
22
+ "chunk_size_feed_forward": 0,
23
+ "cross_attention_hidden_size": null,
24
+ "decoder_start_token_id": null,
25
+ "delta_model_name_or_path": null,
26
+ "diversity_penalty": 0.0,
27
+ "do_sample": false,
28
+ "early_stopping": false,
29
+ "encoder_no_repeat_ngram_size": 0,
30
+ "eos_token_id": null,
31
+ "exponential_decay_length_penalty": null,
32
+ "finetuning_task": null,
33
+ "forced_bos_token_id": null,
34
+ "forced_eos_token_id": null,
35
+ "id2label": {
36
+ "0": "LABEL_0",
37
+ "1": "LABEL_1"
38
+ },
39
+ "is_decoder": false,
40
+ "is_encoder_decoder": false,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1
44
+ },
45
+ "length_penalty": 1.0,
46
+ "max_length": 20,
47
+ "min_length": 0,
48
+ "model_type": "mllm_lm",
49
+ "no_repeat_ngram_size": 0,
50
+ "num_beam_groups": 1,
51
+ "num_beams": 1,
52
+ "num_return_sequences": 1,
53
+ "output_attentions": false,
54
+ "output_hidden_states": false,
55
+ "output_scores": false,
56
+ "pad_token_id": null,
57
+ "prefix": null,
58
+ "pretrained_lm_name_or_path": "/hbox2dir/vicuna-13b-v1.5",
59
+ "pretrained_tokenizer_name_or_path": "/hbox2dir/vicuna-13b-v1.5",
60
+ "problem_type": null,
61
+ "pruned_heads": {},
62
+ "remove_invalid_values": false,
63
+ "repetition_penalty": 1.0,
64
+ "return_dict": true,
65
+ "return_dict_in_generate": false,
66
+ "sep_token_id": null,
67
+ "suppress_tokens": null,
68
+ "task_specific_params": null,
69
+ "temperature": 1.0,
70
+ "tf_legacy_loss": false,
71
+ "tie_encoder_decoder": false,
72
+ "tie_word_embeddings": true,
73
+ "tokenizer_class": null,
74
+ "top_k": 50,
75
+ "top_p": 1.0,
76
+ "torch_dtype": null,
77
+ "torchscript": false,
78
+ "transformers_version": "4.30.2",
79
+ "typical_p": 1.0,
80
+ "use_bfloat16": false
81
+ },
82
+ "max_position_embeddings": 4096,
83
+ "model_type": "mllm",
84
+ "num_attention_heads": 40,
85
+ "num_hidden_layers": 40,
86
+ "num_key_value_heads": 40,
87
+ "num_query_tokens": 576,
88
+ "pretraining_tp": 1,
89
+ "rms_norm_eps": 1e-05,
90
+ "rope_scaling": null,
91
+ "text_config": {
92
+ "_name_or_path": "",
93
+ "add_cross_attention": false,
94
+ "architectures": [
95
+ "LlamaForCausalLM"
96
+ ],
97
+ "bad_words_ids": null,
98
+ "begin_suppress_tokens": null,
99
+ "bos_token_id": 1,
100
+ "chunk_size_feed_forward": 0,
101
+ "cross_attention_hidden_size": null,
102
+ "decoder_start_token_id": null,
103
+ "diversity_penalty": 0.0,
104
+ "do_sample": false,
105
+ "early_stopping": false,
106
+ "encoder_no_repeat_ngram_size": 0,
107
+ "eos_token_id": 2,
108
+ "exponential_decay_length_penalty": null,
109
+ "finetuning_task": null,
110
+ "forced_bos_token_id": null,
111
+ "forced_eos_token_id": null,
112
+ "hidden_act": "silu",
113
+ "hidden_size": 5120,
114
+ "id2label": {
115
+ "0": "LABEL_0",
116
+ "1": "LABEL_1"
117
+ },
118
+ "initializer_range": 0.02,
119
+ "intermediate_size": 13824,
120
+ "is_decoder": false,
121
+ "is_encoder_decoder": false,
122
+ "label2id": {
123
+ "LABEL_0": 0,
124
+ "LABEL_1": 1
125
+ },
126
+ "length_penalty": 1.0,
127
+ "max_length": 4096,
128
+ "max_position_embeddings": 4096,
129
+ "min_length": 0,
130
+ "model_type": "llama",
131
+ "no_repeat_ngram_size": 0,
132
+ "num_attention_heads": 40,
133
+ "num_beam_groups": 1,
134
+ "num_beams": 1,
135
+ "num_hidden_layers": 40,
136
+ "num_key_value_heads": 40,
137
+ "num_return_sequences": 1,
138
+ "output_attentions": false,
139
+ "output_hidden_states": false,
140
+ "output_scores": false,
141
+ "pad_token_id": 0,
142
+ "prefix": null,
143
+ "pretraining_tp": 1,
144
+ "problem_type": null,
145
+ "pruned_heads": {},
146
+ "remove_invalid_values": false,
147
+ "repetition_penalty": 1.0,
148
+ "return_dict": true,
149
+ "return_dict_in_generate": false,
150
+ "rms_norm_eps": 1e-05,
151
+ "rope_scaling": null,
152
+ "sep_token_id": null,
153
+ "suppress_tokens": null,
154
+ "task_specific_params": null,
155
+ "temperature": 1.0,
156
+ "tf_legacy_loss": false,
157
+ "tie_encoder_decoder": false,
158
+ "tie_word_embeddings": false,
159
+ "tokenizer_class": null,
160
+ "top_k": 50,
161
+ "top_p": 1.0,
162
+ "torch_dtype": "float16",
163
+ "torchscript": false,
164
+ "transformers_version": "4.30.2",
165
+ "typical_p": 1.0,
166
+ "use_bfloat16": false,
167
+ "use_cache": true,
168
+ "vocab_size": 32000
169
+ },
170
+ "tie_word_embeddings": false,
171
+ "torch_dtype": "bfloat16",
172
+ "transformers_version": null,
173
+ "use_cache": true,
174
+ "use_decoder_only_language_model": true,
175
+ "vision_config": {
176
+ "_name_or_path": "",
177
+ "add_cross_attention": false,
178
+ "architectures": null,
179
+ "attention_dropout": 0.0,
180
+ "bad_words_ids": null,
181
+ "begin_suppress_tokens": null,
182
+ "bos_token_id": null,
183
+ "chunk_size_feed_forward": 0,
184
+ "cross_attention_hidden_size": null,
185
+ "decoder_start_token_id": null,
186
+ "diversity_penalty": 0.0,
187
+ "do_sample": false,
188
+ "dropout": 0.0,
189
+ "early_stopping": false,
190
+ "encoder_no_repeat_ngram_size": 0,
191
+ "encoder_type": "openai.clip",
192
+ "eos_token_id": null,
193
+ "exponential_decay_length_penalty": null,
194
+ "finetuning_task": null,
195
+ "forced_bos_token_id": null,
196
+ "forced_eos_token_id": null,
197
+ "hidden_act": "quick_gelu",
198
+ "hidden_size": 1024,
199
+ "id2label": {
200
+ "0": "LABEL_0",
201
+ "1": "LABEL_1"
202
+ },
203
+ "image_size": 336,
204
+ "initializer_factor": 1.0,
205
+ "initializer_range": 0.02,
206
+ "intermediate_size": 4096,
207
+ "is_decoder": false,
208
+ "is_encoder_decoder": false,
209
+ "label2id": {
210
+ "LABEL_0": 0,
211
+ "LABEL_1": 1
212
+ },
213
+ "layer_norm_eps": 1e-05,
214
+ "length_penalty": 1.0,
215
+ "max_length": 20,
216
+ "min_length": 0,
217
+ "model_type": "clip_vision_model",
218
+ "no_repeat_ngram_size": 0,
219
+ "num_attention_heads": 16,
220
+ "num_beam_groups": 1,
221
+ "num_beams": 1,
222
+ "num_channels": 3,
223
+ "num_hidden_layers": 24,
224
+ "num_return_sequences": 1,
225
+ "output_attentions": false,
226
+ "output_hidden_states": false,
227
+ "output_scores": false,
228
+ "pad_token_id": null,
229
+ "patch_size": 14,
230
+ "prefix": null,
231
+ "pretrained_vision_name_or_path": "/hbox2dir/clip-vit-large-patch14-336",
232
+ "problem_type": null,
233
+ "projection_dim": 768,
234
+ "pruned_heads": {},
235
+ "remove_invalid_values": false,
236
+ "repetition_penalty": 1.0,
237
+ "return_dict": true,
238
+ "return_dict_in_generate": false,
239
+ "sep_token_id": null,
240
+ "suppress_tokens": null,
241
+ "task_specific_params": null,
242
+ "temperature": 1.0,
243
+ "tf_legacy_loss": false,
244
+ "tie_encoder_decoder": false,
245
+ "tie_word_embeddings": true,
246
+ "tokenizer_class": null,
247
+ "top_k": 50,
248
+ "top_p": 1.0,
249
+ "torch_dtype": null,
250
+ "torchscript": false,
251
+ "transformers_version": "4.30.2",
252
+ "typical_p": 1.0,
253
+ "use_bfloat16": false
254
+ },
255
+ "visual_projector_config": {
256
+ "_name_or_path": "",
257
+ "add_cross_attention": false,
258
+ "architectures": null,
259
+ "attention_probs_dropout_prob": 0.1,
260
+ "bad_words_ids": null,
261
+ "begin_suppress_tokens": null,
262
+ "bos_token_id": null,
263
+ "chunk_size_feed_forward": 0,
264
+ "cross_attention_hidden_size": null,
265
+ "decoder_start_token_id": null,
266
+ "depth": 3,
267
+ "diversity_penalty": 0.0,
268
+ "do_sample": false,
269
+ "early_stopping": false,
270
+ "encoder_hidden_size": 1024,
271
+ "encoder_no_repeat_ngram_size": 0,
272
+ "eos_token_id": null,
273
+ "exponential_decay_length_penalty": null,
274
+ "feature_layer_index": -2,
275
+ "finetuning_task": null,
276
+ "forced_bos_token_id": null,
277
+ "forced_eos_token_id": null,
278
+ "hidden_size": 1024,
279
+ "id2label": {
280
+ "0": "LABEL_0",
281
+ "1": "LABEL_1"
282
+ },
283
+ "initializer_range": 0.02,
284
+ "intermediate_size": 4096,
285
+ "is_decoder": false,
286
+ "is_encoder_decoder": false,
287
+ "label2id": {
288
+ "LABEL_0": 0,
289
+ "LABEL_1": 1
290
+ },
291
+ "layer_norm_eps": 1e-06,
292
+ "length_penalty": 1.0,
293
+ "max_length": 20,
294
+ "min_length": 0,
295
+ "mlp_depth": 2,
296
+ "model_type": "mllm_visual_projector",
297
+ "no_repeat_ngram_size": 0,
298
+ "num_attention_heads": 16,
299
+ "num_beam_groups": 1,
300
+ "num_beams": 1,
301
+ "num_eos_tokens": 0,
302
+ "num_hidden_layers": 6,
303
+ "num_queries": 576,
304
+ "num_return_sequences": 1,
305
+ "output_attentions": false,
306
+ "output_hidden_states": false,
307
+ "output_scores": false,
308
+ "pad_token_id": null,
309
+ "pos_emb": true,
310
+ "prefix": null,
311
+ "prenorm": false,
312
+ "problem_type": null,
313
+ "projector_type": "c-abs",
314
+ "pruned_heads": {},
315
+ "remove_invalid_values": false,
316
+ "repetition_penalty": 1.0,
317
+ "return_dict": true,
318
+ "return_dict_in_generate": false,
319
+ "sep_token_id": null,
320
+ "suppress_tokens": null,
321
+ "task_specific_params": null,
322
+ "temperature": 1.0,
323
+ "tf_legacy_loss": false,
324
+ "tie_encoder_decoder": false,
325
+ "tie_word_embeddings": true,
326
+ "tokenizer_class": null,
327
+ "top_k": 50,
328
+ "top_p": 1.0,
329
+ "torch_dtype": null,
330
+ "torchscript": false,
331
+ "transformers_version": "4.30.2",
332
+ "typical_p": 1.0,
333
+ "use_bfloat16": false,
334
+ "use_cls": true
335
+ },
336
+ "vocab_size": 32000
337
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|end_of_text|>"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,2064 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|end_of_text|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 2048,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "padding_side": "right",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
2064
+ }