Hugging Face's logo

gw49
/
EMIT-8B

Safetensors
internvl_chat
custom_code
Model card Files
xet
Community
gw49 commited on
Commit
7a5d6a6
·
verified ·
1 Parent(s): 5199765

Upload 12 files

Browse files
Files changed (12) hide show
  1. added_tokens.json +34 -0
  2. config.json +224 -0
  3. generation_config.json +4 -0
  4. merges.txt +0 -0
  5. model-00001-of-00004.safetensors +3 -0
  6. model-00002-of-00004.safetensors +3 -0
  7. model-00003-of-00004.safetensors +3 -0
  8. model-00004-of-00004.safetensors +3 -0
  9. model.safetensors.index.json +700 -0
  10. special_tokens_map.json +31 -0
  11. tokenizer_config.json +289 -0
  12. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 151673,
3
+ "</img>": 151666,
4
+ "</quad>": 151669,
5
+ "</ref>": 151671,
6
+ "</tool_call>": 151658,
7
+ "<COMP_CONTEXT>": 151674,
8
+ "<IMG_CONTEXT>": 151667,
9
+ "<box>": 151672,
10
+ "<img>": 151665,
11
+ "<quad>": 151668,
12
+ "<ref>": 151670,
13
+ "<tool_call>": 151657,
14
+ "<|box_end|>": 151649,
15
+ "<|box_start|>": 151648,
16
+ "<|endoftext|>": 151643,
17
+ "<|file_sep|>": 151664,
18
+ "<|fim_middle|>": 151660,
19
+ "<|fim_pad|>": 151662,
20
+ "<|fim_prefix|>": 151659,
21
+ "<|fim_suffix|>": 151661,
22
+ "<|im_end|>": 151645,
23
+ "<|im_start|>": 151644,
24
+ "<|image_pad|>": 151655,
25
+ "<|object_ref_end|>": 151647,
26
+ "<|object_ref_start|>": 151646,
27
+ "<|quad_end|>": 151651,
28
+ "<|quad_start|>": 151650,
29
+ "<|repo_name|>": 151663,
30
+ "<|video_pad|>": 151656,
31
+ "<|vision_end|>": 151653,
32
+ "<|vision_pad|>": 151654,
33
+ "<|vision_start|>": 151652
34
+ }
config.json ADDED
@@ -0,0 +1,224 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "architectures": [
4
+ "CustomizedInternVLChatModel"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
8
+ "AutoModel": "modeling_internvl_chat.InternVLChatModel",
9
+ "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel"
10
+ },
11
+ "downsample_ratio": 0.5,
12
+ "dynamic_image_size": true,
13
+ "force_image_size": 448,
14
+ "hidden_size": 3584,
15
+ "image_fold": null,
16
+ "llm_config": {
17
+ "_attn_implementation_autoset": true,
18
+ "_name_or_path": "./pretrained/Qwen2.5-32B-Instruct",
19
+ "add_cross_attention": false,
20
+ "architectures": [
21
+ "Qwen2ForCausalLM"
22
+ ],
23
+ "attention_dropout": 0.0,
24
+ "attn_implementation": "flash_attention_2",
25
+ "bad_words_ids": null,
26
+ "begin_suppress_tokens": null,
27
+ "bos_token_id": 151643,
28
+ "chunk_size_feed_forward": 0,
29
+ "cross_attention_hidden_size": null,
30
+ "decoder_start_token_id": null,
31
+ "diversity_penalty": 0.0,
32
+ "do_sample": false,
33
+ "early_stopping": false,
34
+ "encoder_no_repeat_ngram_size": 0,
35
+ "eos_token_id": 151643,
36
+ "exponential_decay_length_penalty": null,
37
+ "finetuning_task": null,
38
+ "forced_bos_token_id": null,
39
+ "forced_eos_token_id": null,
40
+ "hidden_act": "silu",
41
+ "hidden_size": 3584,
42
+ "id2label": {
43
+ "0": "LABEL_0",
44
+ "1": "LABEL_1"
45
+ },
46
+ "initializer_range": 0.02,
47
+ "intermediate_size": 18944,
48
+ "is_decoder": false,
49
+ "is_encoder_decoder": false,
50
+ "label2id": {
51
+ "LABEL_0": 0,
52
+ "LABEL_1": 1
53
+ },
54
+ "length_penalty": 1.0,
55
+ "max_length": 20,
56
+ "max_position_embeddings": 32768,
57
+ "max_window_layers": 70,
58
+ "min_length": 0,
59
+ "model_type": "qwen2",
60
+ "moe_config": null,
61
+ "no_repeat_ngram_size": 0,
62
+ "num_attention_heads": 28,
63
+ "num_beam_groups": 1,
64
+ "num_beams": 1,
65
+ "num_hidden_layers": 28,
66
+ "num_key_value_heads": 4,
67
+ "num_return_sequences": 1,
68
+ "output_attentions": false,
69
+ "output_hidden_states": false,
70
+ "output_scores": false,
71
+ "pad_token_id": null,
72
+ "prefix": null,
73
+ "problem_type": null,
74
+ "pruned_heads": {},
75
+ "remove_invalid_values": false,
76
+ "repetition_penalty": 1.0,
77
+ "return_dict": true,
78
+ "return_dict_in_generate": false,
79
+ "rms_norm_eps": 1e-06,
80
+ "rope_scaling": {
81
+ "factor": 2.0,
82
+ "rope_type": "dynamic",
83
+ "type": "dynamic"
84
+ },
85
+ "rope_theta": 1000000.0,
86
+ "sep_token_id": null,
87
+ "sliding_window": null,
88
+ "suppress_tokens": null,
89
+ "task_specific_params": null,
90
+ "temperature": 1.0,
91
+ "tf_legacy_loss": false,
92
+ "tie_encoder_decoder": false,
93
+ "tie_word_embeddings": false,
94
+ "tokenizer_class": null,
95
+ "top_k": 50,
96
+ "top_p": 1.0,
97
+ "torch_dtype": "bfloat16",
98
+ "torchscript": false,
99
+ "transformers_version": "4.50.0",
100
+ "typical_p": 1.0,
101
+ "use_bfloat16": true,
102
+ "use_cache": false,
103
+ "use_sliding_window": false,
104
+ "vocab_size": 151675
105
+ },
106
+ "max_dynamic_patch": 12,
107
+ "min_dynamic_patch": 1,
108
+ "model_type": "internvl_chat",
109
+ "pad2square": false,
110
+ "ps_version": "v2",
111
+ "select_layer": -1,
112
+ "system_message": null,
113
+ "template": "internvl2_5",
114
+ "tie_word_embeddings": false,
115
+ "torch_dtype": "bfloat16",
116
+ "transformers_version": null,
117
+ "use_backbone_lora": 0,
118
+ "use_llm_lora": 0,
119
+ "use_thumbnail": true,
120
+ "vision_config": {
121
+ "_attn_implementation_autoset": true,
122
+ "_name_or_path": "OpenGVLab/InternViT-6B-448px-V1-5",
123
+ "add_cross_attention": false,
124
+ "architectures": [
125
+ "InternVisionModel"
126
+ ],
127
+ "attention_dropout": 0.0,
128
+ "auto_map": {
129
+ "AutoConfig": "configuration_intern_vit.InternVisionConfig",
130
+ "AutoModel": "modeling_intern_vit.InternVisionModel"
131
+ },
132
+ "bad_words_ids": null,
133
+ "begin_suppress_tokens": null,
134
+ "bos_token_id": null,
135
+ "capacity_factor": 1.2,
136
+ "chunk_size_feed_forward": 0,
137
+ "cross_attention_hidden_size": null,
138
+ "decoder_start_token_id": null,
139
+ "diversity_penalty": 0.0,
140
+ "do_sample": false,
141
+ "drop_path_rate": 0.1,
142
+ "dropout": 0.0,
143
+ "early_stopping": false,
144
+ "encoder_no_repeat_ngram_size": 0,
145
+ "eos_token_id": null,
146
+ "eval_capacity_factor": 1.4,
147
+ "exponential_decay_length_penalty": null,
148
+ "finetuning_task": null,
149
+ "forced_bos_token_id": null,
150
+ "forced_eos_token_id": null,
151
+ "hidden_act": "gelu",
152
+ "hidden_size": 1024,
153
+ "id2label": {
154
+ "0": "LABEL_0",
155
+ "1": "LABEL_1"
156
+ },
157
+ "image_size": 448,
158
+ "initializer_factor": 0.1,
159
+ "initializer_range": 1e-10,
160
+ "intermediate_size": 4096,
161
+ "is_decoder": false,
162
+ "is_encoder_decoder": false,
163
+ "label2id": {
164
+ "LABEL_0": 0,
165
+ "LABEL_1": 1
166
+ },
167
+ "laux_allreduce": "all_nodes",
168
+ "layer_norm_eps": 1e-06,
169
+ "length_penalty": 1.0,
170
+ "max_length": 20,
171
+ "min_length": 0,
172
+ "model_type": "intern_vit_6b",
173
+ "moe_coeff_ratio": 0.5,
174
+ "moe_intermediate_size": 768,
175
+ "moe_output_scale": 4.0,
176
+ "no_repeat_ngram_size": 0,
177
+ "noisy_gate_policy": "RSample_before",
178
+ "norm_type": "layer_norm",
179
+ "num_attention_heads": 16,
180
+ "num_beam_groups": 1,
181
+ "num_beams": 1,
182
+ "num_channels": 3,
183
+ "num_experts": 8,
184
+ "num_hidden_layers": 24,
185
+ "num_return_sequences": 1,
186
+ "num_routed_experts": 4,
187
+ "num_shared_experts": 4,
188
+ "output_attentions": false,
189
+ "output_hidden_states": false,
190
+ "output_scores": false,
191
+ "pad_token_id": null,
192
+ "patch_size": 14,
193
+ "prefix": null,
194
+ "problem_type": null,
195
+ "pruned_heads": {},
196
+ "qk_normalization": false,
197
+ "qkv_bias": true,
198
+ "remove_invalid_values": false,
199
+ "repetition_penalty": 1.0,
200
+ "return_dict": true,
201
+ "return_dict_in_generate": false,
202
+ "sep_token_id": null,
203
+ "shared_expert_intermediate_size": 3072,
204
+ "suppress_tokens": null,
205
+ "task_specific_params": null,
206
+ "temperature": 1.0,
207
+ "tf_legacy_loss": false,
208
+ "tie_encoder_decoder": false,
209
+ "tie_word_embeddings": true,
210
+ "tokenizer_class": null,
211
+ "top_k": 50,
212
+ "top_p": 1.0,
213
+ "torch_dtype": "bfloat16",
214
+ "torchscript": false,
215
+ "transformers_version": "4.50.0",
216
+ "typical_p": 1.0,
217
+ "use_bfloat16": true,
218
+ "use_flash_attn": true,
219
+ "use_moe": false,
220
+ "use_residual": true,
221
+ "use_rts": false,
222
+ "use_weighted_residual": false
223
+ }
224
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.50.0"
4
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34a5d15032664cff1ec82a7d415142a0e5c89d85291c040f269c9b438f733426
3
+ size 4991131128
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb2e3ea94a4e5dd66d6cf9c8e70cca73ae9b418392be7eeae84c65b70b49b46c
3
+ size 4958443072
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9c1cc768b155edeadbc294602b26dd7d55ce85c1680316d0e82ffbd495b8c0f
3
+ size 4796984024
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2ad04e1ea56f234d95be2a9fdd06dde307fc0b50c89964b63ac5c957c56d5ea
3
+ size 1142475144
model.safetensors.index.json ADDED
@@ -0,0 +1,700 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15888948240
4
+ },
5
+ "weight_map": {
6
+ "language_model.lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "language_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "language_model.model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
14
+ "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
15
+ "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
16
+ "language_model.model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
17
+ "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
18
+ "language_model.model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
19
+ "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
20
+ "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
21
+ "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
22
+ "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
23
+ "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
24
+ "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
25
+ "language_model.model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
26
+ "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
27
+ "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
28
+ "language_model.model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
29
+ "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
30
+ "language_model.model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
31
+ "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
32
+ "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
33
+ "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
34
+ "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
35
+ "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
36
+ "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
37
+ "language_model.model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
38
+ "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
39
+ "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
40
+ "language_model.model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
41
+ "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
42
+ "language_model.model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
43
+ "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "language_model.model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
50
+ "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
51
+ "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
52
+ "language_model.model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
53
+ "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
54
+ "language_model.model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
55
+ "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
56
+ "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
57
+ "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
58
+ "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
59
+ "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
60
+ "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
61
+ "language_model.model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
62
+ "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
63
+ "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
64
+ "language_model.model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
65
+ "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
66
+ "language_model.model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
67
+ "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
68
+ "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
69
+ "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
70
+ "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
71
+ "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
72
+ "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
73
+ "language_model.model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
74
+ "language_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
75
+ "language_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
76
+ "language_model.model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
77
+ "language_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
78
+ "language_model.model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
79
+ "language_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "language_model.model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
86
+ "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
87
+ "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
88
+ "language_model.model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
89
+ "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
90
+ "language_model.model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
91
+ "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
92
+ "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
93
+ "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
94
+ "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
95
+ "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
96
+ "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
97
+ "language_model.model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
98
+ "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
99
+ "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
100
+ "language_model.model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
101
+ "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
102
+ "language_model.model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
103
+ "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
104
+ "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
105
+ "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
106
+ "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
107
+ "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
108
+ "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
109
+ "language_model.model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
110
+ "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
111
+ "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
112
+ "language_model.model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
113
+ "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
114
+ "language_model.model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
115
+ "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
117
+ "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
118
+ "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
119
+ "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
120
+ "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
121
+ "language_model.model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
122
+ "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
123
+ "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
124
+ "language_model.model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
125
+ "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
126
+ "language_model.model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
127
+ "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
128
+ "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
129
+ "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
130
+ "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
131
+ "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
132
+ "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
133
+ "language_model.model.layers.18.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
134
+ "language_model.model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
135
+ "language_model.model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
136
+ "language_model.model.layers.18.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
137
+ "language_model.model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
138
+ "language_model.model.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
139
+ "language_model.model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
140
+ "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
141
+ "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
142
+ "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
143
+ "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
144
+ "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
145
+ "language_model.model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
146
+ "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
147
+ "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
148
+ "language_model.model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
149
+ "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
150
+ "language_model.model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
151
+ "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
153
+ "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
154
+ "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
155
+ "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
156
+ "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
157
+ "language_model.model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
158
+ "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
159
+ "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
160
+ "language_model.model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
161
+ "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
162
+ "language_model.model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
163
+ "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
164
+ "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
165
+ "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
166
+ "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
167
+ "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
168
+ "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
169
+ "language_model.model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
170
+ "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
171
+ "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
172
+ "language_model.model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
173
+ "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
174
+ "language_model.model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
175
+ "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
176
+ "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
177
+ "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
178
+ "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
179
+ "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
180
+ "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
181
+ "language_model.model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
182
+ "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
183
+ "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
184
+ "language_model.model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
185
+ "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
186
+ "language_model.model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
187
+ "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "language_model.model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
194
+ "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
195
+ "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
196
+ "language_model.model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
197
+ "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
198
+ "language_model.model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
199
+ "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
200
+ "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
201
+ "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
202
+ "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
203
+ "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
204
+ "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
205
+ "language_model.model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
206
+ "language_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
207
+ "language_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
208
+ "language_model.model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
209
+ "language_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
210
+ "language_model.model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
211
+ "language_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
212
+ "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
213
+ "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
214
+ "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
215
+ "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
216
+ "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
217
+ "language_model.model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
218
+ "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
219
+ "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
220
+ "language_model.model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
221
+ "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
222
+ "language_model.model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
223
+ "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
224
+ "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "language_model.model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
230
+ "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
231
+ "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
232
+ "language_model.model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
233
+ "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
234
+ "language_model.model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
235
+ "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
236
+ "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
237
+ "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
238
+ "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
239
+ "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
240
+ "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
241
+ "language_model.model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
242
+ "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
243
+ "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
244
+ "language_model.model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
245
+ "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
246
+ "language_model.model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
247
+ "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
248
+ "language_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
249
+ "language_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
250
+ "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
251
+ "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
252
+ "language_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
253
+ "language_model.model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
254
+ "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
255
+ "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
256
+ "language_model.model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
257
+ "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
258
+ "language_model.model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
259
+ "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
260
+ "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "language_model.model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
266
+ "language_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
267
+ "language_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
268
+ "language_model.model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
269
+ "language_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
270
+ "language_model.model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
271
+ "language_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
272
+ "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
273
+ "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
274
+ "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
275
+ "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
276
+ "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
277
+ "language_model.model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
278
+ "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
279
+ "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
280
+ "language_model.model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
281
+ "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
282
+ "language_model.model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
283
+ "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
284
+ "language_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
285
+ "language_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
286
+ "language_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
287
+ "language_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
288
+ "language_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
289
+ "language_model.model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
290
+ "language_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
291
+ "language_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
292
+ "language_model.model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
293
+ "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
294
+ "language_model.model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
295
+ "language_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
296
+ "language_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
297
+ "language_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
298
+ "language_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
299
+ "language_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
300
+ "language_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
301
+ "language_model.model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
302
+ "language_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
303
+ "language_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
304
+ "language_model.model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
305
+ "language_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
306
+ "language_model.model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
307
+ "language_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
308
+ "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
309
+ "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
310
+ "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
311
+ "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
312
+ "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
313
+ "language_model.model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
314
+ "language_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
315
+ "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
316
+ "language_model.model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
317
+ "language_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
318
+ "language_model.model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
319
+ "language_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
320
+ "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
321
+ "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
322
+ "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
323
+ "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
324
+ "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
325
+ "language_model.model.layers.8.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
326
+ "language_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
327
+ "language_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
328
+ "language_model.model.layers.8.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
329
+ "language_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
330
+ "language_model.model.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
331
+ "language_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
332
+ "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
333
+ "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
334
+ "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
335
+ "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
336
+ "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
337
+ "language_model.model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
338
+ "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
339
+ "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
340
+ "language_model.model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
341
+ "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
342
+ "language_model.model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
343
+ "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
344
+ "language_model.model.norm.weight": "model-00003-of-00004.safetensors",
345
+ "mlp1.0.bias": "model-00004-of-00004.safetensors",
346
+ "mlp1.0.weight": "model-00004-of-00004.safetensors",
347
+ "mlp1.1.bias": "model-00004-of-00004.safetensors",
348
+ "mlp1.1.weight": "model-00004-of-00004.safetensors",
349
+ "mlp1.3.bias": "model-00004-of-00004.safetensors",
350
+ "mlp1.3.weight": "model-00004-of-00004.safetensors",
351
+ "projector.0.bias": "model-00004-of-00004.safetensors",
352
+ "projector.0.num_batches_tracked": "model-00004-of-00004.safetensors",
353
+ "projector.0.running_mean": "model-00004-of-00004.safetensors",
354
+ "projector.0.running_var": "model-00004-of-00004.safetensors",
355
+ "projector.0.weight": "model-00004-of-00004.safetensors",
356
+ "projector.1.bias": "model-00004-of-00004.safetensors",
357
+ "projector.1.weight": "model-00004-of-00004.safetensors",
358
+ "soft_prompt.weight": "model-00004-of-00004.safetensors",
359
+ "vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
360
+ "vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
361
+ "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
362
+ "vision_model.embeddings.position_embedding": "model-00001-of-00004.safetensors",
363
+ "vision_model.encoder.layers.0.attn.proj.bias": "model-00001-of-00004.safetensors",
364
+ "vision_model.encoder.layers.0.attn.proj.weight": "model-00001-of-00004.safetensors",
365
+ "vision_model.encoder.layers.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
366
+ "vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
367
+ "vision_model.encoder.layers.0.ls1": "model-00001-of-00004.safetensors",
368
+ "vision_model.encoder.layers.0.ls2": "model-00001-of-00004.safetensors",
369
+ "vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
370
+ "vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
371
+ "vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
372
+ "vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
373
+ "vision_model.encoder.layers.0.norm1.bias": "model-00001-of-00004.safetensors",
374
+ "vision_model.encoder.layers.0.norm1.weight": "model-00001-of-00004.safetensors",
375
+ "vision_model.encoder.layers.0.norm2.bias": "model-00001-of-00004.safetensors",
376
+ "vision_model.encoder.layers.0.norm2.weight": "model-00001-of-00004.safetensors",
377
+ "vision_model.encoder.layers.1.attn.proj.bias": "model-00001-of-00004.safetensors",
378
+ "vision_model.encoder.layers.1.attn.proj.weight": "model-00001-of-00004.safetensors",
379
+ "vision_model.encoder.layers.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
380
+ "vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
381
+ "vision_model.encoder.layers.1.ls1": "model-00001-of-00004.safetensors",
382
+ "vision_model.encoder.layers.1.ls2": "model-00001-of-00004.safetensors",
383
+ "vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
384
+ "vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
385
+ "vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
386
+ "vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
387
+ "vision_model.encoder.layers.1.norm1.bias": "model-00001-of-00004.safetensors",
388
+ "vision_model.encoder.layers.1.norm1.weight": "model-00001-of-00004.safetensors",
389
+ "vision_model.encoder.layers.1.norm2.bias": "model-00001-of-00004.safetensors",
390
+ "vision_model.encoder.layers.1.norm2.weight": "model-00001-of-00004.safetensors",
391
+ "vision_model.encoder.layers.10.attn.proj.bias": "model-00001-of-00004.safetensors",
392
+ "vision_model.encoder.layers.10.attn.proj.weight": "model-00001-of-00004.safetensors",
393
+ "vision_model.encoder.layers.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
394
+ "vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
395
+ "vision_model.encoder.layers.10.ls1": "model-00001-of-00004.safetensors",
396
+ "vision_model.encoder.layers.10.ls2": "model-00001-of-00004.safetensors",
397
+ "vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
398
+ "vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
399
+ "vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
400
+ "vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
401
+ "vision_model.encoder.layers.10.norm1.bias": "model-00001-of-00004.safetensors",
402
+ "vision_model.encoder.layers.10.norm1.weight": "model-00001-of-00004.safetensors",
403
+ "vision_model.encoder.layers.10.norm2.bias": "model-00001-of-00004.safetensors",
404
+ "vision_model.encoder.layers.10.norm2.weight": "model-00001-of-00004.safetensors",
405
+ "vision_model.encoder.layers.11.attn.proj.bias": "model-00001-of-00004.safetensors",
406
+ "vision_model.encoder.layers.11.attn.proj.weight": "model-00001-of-00004.safetensors",
407
+ "vision_model.encoder.layers.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
408
+ "vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
409
+ "vision_model.encoder.layers.11.ls1": "model-00001-of-00004.safetensors",
410
+ "vision_model.encoder.layers.11.ls2": "model-00001-of-00004.safetensors",
411
+ "vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
412
+ "vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
413
+ "vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
414
+ "vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
415
+ "vision_model.encoder.layers.11.norm1.bias": "model-00001-of-00004.safetensors",
416
+ "vision_model.encoder.layers.11.norm1.weight": "model-00001-of-00004.safetensors",
417
+ "vision_model.encoder.layers.11.norm2.bias": "model-00001-of-00004.safetensors",
418
+ "vision_model.encoder.layers.11.norm2.weight": "model-00001-of-00004.safetensors",
419
+ "vision_model.encoder.layers.12.attn.proj.bias": "model-00001-of-00004.safetensors",
420
+ "vision_model.encoder.layers.12.attn.proj.weight": "model-00001-of-00004.safetensors",
421
+ "vision_model.encoder.layers.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
422
+ "vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
423
+ "vision_model.encoder.layers.12.ls1": "model-00001-of-00004.safetensors",
424
+ "vision_model.encoder.layers.12.ls2": "model-00001-of-00004.safetensors",
425
+ "vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
426
+ "vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
427
+ "vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
428
+ "vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
429
+ "vision_model.encoder.layers.12.norm1.bias": "model-00001-of-00004.safetensors",
430
+ "vision_model.encoder.layers.12.norm1.weight": "model-00001-of-00004.safetensors",
431
+ "vision_model.encoder.layers.12.norm2.bias": "model-00001-of-00004.safetensors",
432
+ "vision_model.encoder.layers.12.norm2.weight": "model-00001-of-00004.safetensors",
433
+ "vision_model.encoder.layers.13.attn.proj.bias": "model-00001-of-00004.safetensors",
434
+ "vision_model.encoder.layers.13.attn.proj.weight": "model-00001-of-00004.safetensors",
435
+ "vision_model.encoder.layers.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
436
+ "vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
437
+ "vision_model.encoder.layers.13.ls1": "model-00001-of-00004.safetensors",
438
+ "vision_model.encoder.layers.13.ls2": "model-00001-of-00004.safetensors",
439
+ "vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
440
+ "vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
441
+ "vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
442
+ "vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
443
+ "vision_model.encoder.layers.13.norm1.bias": "model-00001-of-00004.safetensors",
444
+ "vision_model.encoder.layers.13.norm1.weight": "model-00001-of-00004.safetensors",
445
+ "vision_model.encoder.layers.13.norm2.bias": "model-00001-of-00004.safetensors",
446
+ "vision_model.encoder.layers.13.norm2.weight": "model-00001-of-00004.safetensors",
447
+ "vision_model.encoder.layers.14.attn.proj.bias": "model-00001-of-00004.safetensors",
448
+ "vision_model.encoder.layers.14.attn.proj.weight": "model-00001-of-00004.safetensors",
449
+ "vision_model.encoder.layers.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
450
+ "vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
451
+ "vision_model.encoder.layers.14.ls1": "model-00001-of-00004.safetensors",
452
+ "vision_model.encoder.layers.14.ls2": "model-00001-of-00004.safetensors",
453
+ "vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
454
+ "vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
455
+ "vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
456
+ "vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
457
+ "vision_model.encoder.layers.14.norm1.bias": "model-00001-of-00004.safetensors",
458
+ "vision_model.encoder.layers.14.norm1.weight": "model-00001-of-00004.safetensors",
459
+ "vision_model.encoder.layers.14.norm2.bias": "model-00001-of-00004.safetensors",
460
+ "vision_model.encoder.layers.14.norm2.weight": "model-00001-of-00004.safetensors",
461
+ "vision_model.encoder.layers.15.attn.proj.bias": "model-00001-of-00004.safetensors",
462
+ "vision_model.encoder.layers.15.attn.proj.weight": "model-00001-of-00004.safetensors",
463
+ "vision_model.encoder.layers.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
464
+ "vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
465
+ "vision_model.encoder.layers.15.ls1": "model-00001-of-00004.safetensors",
466
+ "vision_model.encoder.layers.15.ls2": "model-00001-of-00004.safetensors",
467
+ "vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
468
+ "vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
469
+ "vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
470
+ "vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
471
+ "vision_model.encoder.layers.15.norm1.bias": "model-00001-of-00004.safetensors",
472
+ "vision_model.encoder.layers.15.norm1.weight": "model-00001-of-00004.safetensors",
473
+ "vision_model.encoder.layers.15.norm2.bias": "model-00001-of-00004.safetensors",
474
+ "vision_model.encoder.layers.15.norm2.weight": "model-00001-of-00004.safetensors",
475
+ "vision_model.encoder.layers.16.attn.proj.bias": "model-00001-of-00004.safetensors",
476
+ "vision_model.encoder.layers.16.attn.proj.weight": "model-00001-of-00004.safetensors",
477
+ "vision_model.encoder.layers.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
478
+ "vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
479
+ "vision_model.encoder.layers.16.ls1": "model-00001-of-00004.safetensors",
480
+ "vision_model.encoder.layers.16.ls2": "model-00001-of-00004.safetensors",
481
+ "vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
482
+ "vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
483
+ "vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
484
+ "vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
485
+ "vision_model.encoder.layers.16.norm1.bias": "model-00001-of-00004.safetensors",
486
+ "vision_model.encoder.layers.16.norm1.weight": "model-00001-of-00004.safetensors",
487
+ "vision_model.encoder.layers.16.norm2.bias": "model-00001-of-00004.safetensors",
488
+ "vision_model.encoder.layers.16.norm2.weight": "model-00001-of-00004.safetensors",
489
+ "vision_model.encoder.layers.17.attn.proj.bias": "model-00001-of-00004.safetensors",
490
+ "vision_model.encoder.layers.17.attn.proj.weight": "model-00001-of-00004.safetensors",
491
+ "vision_model.encoder.layers.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
492
+ "vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
493
+ "vision_model.encoder.layers.17.ls1": "model-00001-of-00004.safetensors",
494
+ "vision_model.encoder.layers.17.ls2": "model-00001-of-00004.safetensors",
495
+ "vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
496
+ "vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
497
+ "vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
498
+ "vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
499
+ "vision_model.encoder.layers.17.norm1.bias": "model-00001-of-00004.safetensors",
500
+ "vision_model.encoder.layers.17.norm1.weight": "model-00001-of-00004.safetensors",
501
+ "vision_model.encoder.layers.17.norm2.bias": "model-00001-of-00004.safetensors",
502
+ "vision_model.encoder.layers.17.norm2.weight": "model-00001-of-00004.safetensors",
503
+ "vision_model.encoder.layers.18.attn.proj.bias": "model-00001-of-00004.safetensors",
504
+ "vision_model.encoder.layers.18.attn.proj.weight": "model-00001-of-00004.safetensors",
505
+ "vision_model.encoder.layers.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
506
+ "vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
507
+ "vision_model.encoder.layers.18.ls1": "model-00001-of-00004.safetensors",
508
+ "vision_model.encoder.layers.18.ls2": "model-00001-of-00004.safetensors",
509
+ "vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
510
+ "vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
511
+ "vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
512
+ "vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
513
+ "vision_model.encoder.layers.18.norm1.bias": "model-00001-of-00004.safetensors",
514
+ "vision_model.encoder.layers.18.norm1.weight": "model-00001-of-00004.safetensors",
515
+ "vision_model.encoder.layers.18.norm2.bias": "model-00001-of-00004.safetensors",
516
+ "vision_model.encoder.layers.18.norm2.weight": "model-00001-of-00004.safetensors",
517
+ "vision_model.encoder.layers.19.attn.proj.bias": "model-00001-of-00004.safetensors",
518
+ "vision_model.encoder.layers.19.attn.proj.weight": "model-00001-of-00004.safetensors",
519
+ "vision_model.encoder.layers.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
520
+ "vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
521
+ "vision_model.encoder.layers.19.ls1": "model-00001-of-00004.safetensors",
522
+ "vision_model.encoder.layers.19.ls2": "model-00001-of-00004.safetensors",
523
+ "vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
524
+ "vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
525
+ "vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
526
+ "vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
527
+ "vision_model.encoder.layers.19.norm1.bias": "model-00001-of-00004.safetensors",
528
+ "vision_model.encoder.layers.19.norm1.weight": "model-00001-of-00004.safetensors",
529
+ "vision_model.encoder.layers.19.norm2.bias": "model-00001-of-00004.safetensors",
530
+ "vision_model.encoder.layers.19.norm2.weight": "model-00001-of-00004.safetensors",
531
+ "vision_model.encoder.layers.2.attn.proj.bias": "model-00001-of-00004.safetensors",
532
+ "vision_model.encoder.layers.2.attn.proj.weight": "model-00001-of-00004.safetensors",
533
+ "vision_model.encoder.layers.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
534
+ "vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
535
+ "vision_model.encoder.layers.2.ls1": "model-00001-of-00004.safetensors",
536
+ "vision_model.encoder.layers.2.ls2": "model-00001-of-00004.safetensors",
537
+ "vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
538
+ "vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
539
+ "vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
540
+ "vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
541
+ "vision_model.encoder.layers.2.norm1.bias": "model-00001-of-00004.safetensors",
542
+ "vision_model.encoder.layers.2.norm1.weight": "model-00001-of-00004.safetensors",
543
+ "vision_model.encoder.layers.2.norm2.bias": "model-00001-of-00004.safetensors",
544
+ "vision_model.encoder.layers.2.norm2.weight": "model-00001-of-00004.safetensors",
545
+ "vision_model.encoder.layers.20.attn.proj.bias": "model-00001-of-00004.safetensors",
546
+ "vision_model.encoder.layers.20.attn.proj.weight": "model-00001-of-00004.safetensors",
547
+ "vision_model.encoder.layers.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
548
+ "vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
549
+ "vision_model.encoder.layers.20.ls1": "model-00001-of-00004.safetensors",
550
+ "vision_model.encoder.layers.20.ls2": "model-00001-of-00004.safetensors",
551
+ "vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
552
+ "vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
553
+ "vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
554
+ "vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
555
+ "vision_model.encoder.layers.20.norm1.bias": "model-00001-of-00004.safetensors",
556
+ "vision_model.encoder.layers.20.norm1.weight": "model-00001-of-00004.safetensors",
557
+ "vision_model.encoder.layers.20.norm2.bias": "model-00001-of-00004.safetensors",
558
+ "vision_model.encoder.layers.20.norm2.weight": "model-00001-of-00004.safetensors",
559
+ "vision_model.encoder.layers.21.attn.proj.bias": "model-00001-of-00004.safetensors",
560
+ "vision_model.encoder.layers.21.attn.proj.weight": "model-00001-of-00004.safetensors",
561
+ "vision_model.encoder.layers.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
562
+ "vision_model.encoder.layers.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
563
+ "vision_model.encoder.layers.21.ls1": "model-00001-of-00004.safetensors",
564
+ "vision_model.encoder.layers.21.ls2": "model-00001-of-00004.safetensors",
565
+ "vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
566
+ "vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
567
+ "vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
568
+ "vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
569
+ "vision_model.encoder.layers.21.norm1.bias": "model-00001-of-00004.safetensors",
570
+ "vision_model.encoder.layers.21.norm1.weight": "model-00001-of-00004.safetensors",
571
+ "vision_model.encoder.layers.21.norm2.bias": "model-00001-of-00004.safetensors",
572
+ "vision_model.encoder.layers.21.norm2.weight": "model-00001-of-00004.safetensors",
573
+ "vision_model.encoder.layers.22.attn.proj.bias": "model-00001-of-00004.safetensors",
574
+ "vision_model.encoder.layers.22.attn.proj.weight": "model-00001-of-00004.safetensors",
575
+ "vision_model.encoder.layers.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
576
+ "vision_model.encoder.layers.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
577
+ "vision_model.encoder.layers.22.ls1": "model-00001-of-00004.safetensors",
578
+ "vision_model.encoder.layers.22.ls2": "model-00001-of-00004.safetensors",
579
+ "vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
580
+ "vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
581
+ "vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
582
+ "vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
583
+ "vision_model.encoder.layers.22.norm1.bias": "model-00001-of-00004.safetensors",
584
+ "vision_model.encoder.layers.22.norm1.weight": "model-00001-of-00004.safetensors",
585
+ "vision_model.encoder.layers.22.norm2.bias": "model-00001-of-00004.safetensors",
586
+ "vision_model.encoder.layers.22.norm2.weight": "model-00001-of-00004.safetensors",
587
+ "vision_model.encoder.layers.23.attn.proj.bias": "model-00001-of-00004.safetensors",
588
+ "vision_model.encoder.layers.23.attn.proj.weight": "model-00001-of-00004.safetensors",
589
+ "vision_model.encoder.layers.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
590
+ "vision_model.encoder.layers.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
591
+ "vision_model.encoder.layers.23.ls1": "model-00001-of-00004.safetensors",
592
+ "vision_model.encoder.layers.23.ls2": "model-00001-of-00004.safetensors",
593
+ "vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
594
+ "vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
595
+ "vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
596
+ "vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
597
+ "vision_model.encoder.layers.23.norm1.bias": "model-00001-of-00004.safetensors",
598
+ "vision_model.encoder.layers.23.norm1.weight": "model-00001-of-00004.safetensors",
599
+ "vision_model.encoder.layers.23.norm2.bias": "model-00001-of-00004.safetensors",
600
+ "vision_model.encoder.layers.23.norm2.weight": "model-00001-of-00004.safetensors",
601
+ "vision_model.encoder.layers.3.attn.proj.bias": "model-00001-of-00004.safetensors",
602
+ "vision_model.encoder.layers.3.attn.proj.weight": "model-00001-of-00004.safetensors",
603
+ "vision_model.encoder.layers.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
604
+ "vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
605
+ "vision_model.encoder.layers.3.ls1": "model-00001-of-00004.safetensors",
606
+ "vision_model.encoder.layers.3.ls2": "model-00001-of-00004.safetensors",
607
+ "vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
608
+ "vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
609
+ "vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
610
+ "vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
611
+ "vision_model.encoder.layers.3.norm1.bias": "model-00001-of-00004.safetensors",
612
+ "vision_model.encoder.layers.3.norm1.weight": "model-00001-of-00004.safetensors",
613
+ "vision_model.encoder.layers.3.norm2.bias": "model-00001-of-00004.safetensors",
614
+ "vision_model.encoder.layers.3.norm2.weight": "model-00001-of-00004.safetensors",
615
+ "vision_model.encoder.layers.4.attn.proj.bias": "model-00001-of-00004.safetensors",
616
+ "vision_model.encoder.layers.4.attn.proj.weight": "model-00001-of-00004.safetensors",
617
+ "vision_model.encoder.layers.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
618
+ "vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
619
+ "vision_model.encoder.layers.4.ls1": "model-00001-of-00004.safetensors",
620
+ "vision_model.encoder.layers.4.ls2": "model-00001-of-00004.safetensors",
621
+ "vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
622
+ "vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
623
+ "vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
624
+ "vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
625
+ "vision_model.encoder.layers.4.norm1.bias": "model-00001-of-00004.safetensors",
626
+ "vision_model.encoder.layers.4.norm1.weight": "model-00001-of-00004.safetensors",
627
+ "vision_model.encoder.layers.4.norm2.bias": "model-00001-of-00004.safetensors",
628
+ "vision_model.encoder.layers.4.norm2.weight": "model-00001-of-00004.safetensors",
629
+ "vision_model.encoder.layers.5.attn.proj.bias": "model-00001-of-00004.safetensors",
630
+ "vision_model.encoder.layers.5.attn.proj.weight": "model-00001-of-00004.safetensors",
631
+ "vision_model.encoder.layers.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
632
+ "vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
633
+ "vision_model.encoder.layers.5.ls1": "model-00001-of-00004.safetensors",
634
+ "vision_model.encoder.layers.5.ls2": "model-00001-of-00004.safetensors",
635
+ "vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
636
+ "vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
637
+ "vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
638
+ "vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
639
+ "vision_model.encoder.layers.5.norm1.bias": "model-00001-of-00004.safetensors",
640
+ "vision_model.encoder.layers.5.norm1.weight": "model-00001-of-00004.safetensors",
641
+ "vision_model.encoder.layers.5.norm2.bias": "model-00001-of-00004.safetensors",
642
+ "vision_model.encoder.layers.5.norm2.weight": "model-00001-of-00004.safetensors",
643
+ "vision_model.encoder.layers.6.attn.proj.bias": "model-00001-of-00004.safetensors",
644
+ "vision_model.encoder.layers.6.attn.proj.weight": "model-00001-of-00004.safetensors",
645
+ "vision_model.encoder.layers.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
646
+ "vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
647
+ "vision_model.encoder.layers.6.ls1": "model-00001-of-00004.safetensors",
648
+ "vision_model.encoder.layers.6.ls2": "model-00001-of-00004.safetensors",
649
+ "vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
650
+ "vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
651
+ "vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
652
+ "vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
653
+ "vision_model.encoder.layers.6.norm1.bias": "model-00001-of-00004.safetensors",
654
+ "vision_model.encoder.layers.6.norm1.weight": "model-00001-of-00004.safetensors",
655
+ "vision_model.encoder.layers.6.norm2.bias": "model-00001-of-00004.safetensors",
656
+ "vision_model.encoder.layers.6.norm2.weight": "model-00001-of-00004.safetensors",
657
+ "vision_model.encoder.layers.7.attn.proj.bias": "model-00001-of-00004.safetensors",
658
+ "vision_model.encoder.layers.7.attn.proj.weight": "model-00001-of-00004.safetensors",
659
+ "vision_model.encoder.layers.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
660
+ "vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
661
+ "vision_model.encoder.layers.7.ls1": "model-00001-of-00004.safetensors",
662
+ "vision_model.encoder.layers.7.ls2": "model-00001-of-00004.safetensors",
663
+ "vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
664
+ "vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
665
+ "vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
666
+ "vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
667
+ "vision_model.encoder.layers.7.norm1.bias": "model-00001-of-00004.safetensors",
668
+ "vision_model.encoder.layers.7.norm1.weight": "model-00001-of-00004.safetensors",
669
+ "vision_model.encoder.layers.7.norm2.bias": "model-00001-of-00004.safetensors",
670
+ "vision_model.encoder.layers.7.norm2.weight": "model-00001-of-00004.safetensors",
671
+ "vision_model.encoder.layers.8.attn.proj.bias": "model-00001-of-00004.safetensors",
672
+ "vision_model.encoder.layers.8.attn.proj.weight": "model-00001-of-00004.safetensors",
673
+ "vision_model.encoder.layers.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
674
+ "vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
675
+ "vision_model.encoder.layers.8.ls1": "model-00001-of-00004.safetensors",
676
+ "vision_model.encoder.layers.8.ls2": "model-00001-of-00004.safetensors",
677
+ "vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
678
+ "vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
679
+ "vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
680
+ "vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
681
+ "vision_model.encoder.layers.8.norm1.bias": "model-00001-of-00004.safetensors",
682
+ "vision_model.encoder.layers.8.norm1.weight": "model-00001-of-00004.safetensors",
683
+ "vision_model.encoder.layers.8.norm2.bias": "model-00001-of-00004.safetensors",
684
+ "vision_model.encoder.layers.8.norm2.weight": "model-00001-of-00004.safetensors",
685
+ "vision_model.encoder.layers.9.attn.proj.bias": "model-00001-of-00004.safetensors",
686
+ "vision_model.encoder.layers.9.attn.proj.weight": "model-00001-of-00004.safetensors",
687
+ "vision_model.encoder.layers.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
688
+ "vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
689
+ "vision_model.encoder.layers.9.ls1": "model-00001-of-00004.safetensors",
690
+ "vision_model.encoder.layers.9.ls2": "model-00001-of-00004.safetensors",
691
+ "vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
692
+ "vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
693
+ "vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
694
+ "vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
695
+ "vision_model.encoder.layers.9.norm1.bias": "model-00001-of-00004.safetensors",
696
+ "vision_model.encoder.layers.9.norm1.weight": "model-00001-of-00004.safetensors",
697
+ "vision_model.encoder.layers.9.norm2.bias": "model-00001-of-00004.safetensors",
698
+ "vision_model.encoder.layers.9.norm2.weight": "model-00001-of-00004.safetensors"
699
+ }
700
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,289 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "151643": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "151644": {
15
+ "content": "<|im_start|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "151645": {
23
+ "content": "<|im_end|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "151646": {
31
+ "content": "<|object_ref_start|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "151647": {
39
+ "content": "<|object_ref_end|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "151648": {
47
+ "content": "<|box_start|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "151649": {
55
+ "content": "<|box_end|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "151650": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "151651": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "151652": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "151653": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "151654": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "151655": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "151656": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "151657": {
119
+ "content": "<tool_call>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "151658": {
127
+ "content": "</tool_call>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "151659": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "151660": {
143
+ "content": "<|fim_middle|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "151661": {
151
+ "content": "<|fim_suffix|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "151662": {
159
+ "content": "<|fim_pad|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "151663": {
167
+ "content": "<|repo_name|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "151664": {
175
+ "content": "<|file_sep|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ },
182
+ "151665": {
183
+ "content": "<img>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": true
189
+ },
190
+ "151666": {
191
+ "content": "</img>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": true
197
+ },
198
+ "151667": {
199
+ "content": "<IMG_CONTEXT>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": true
205
+ },
206
+ "151668": {
207
+ "content": "<quad>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": true
213
+ },
214
+ "151669": {
215
+ "content": "</quad>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": true
221
+ },
222
+ "151670": {
223
+ "content": "<ref>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "151671": {
231
+ "content": "</ref>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": true
237
+ },
238
+ "151672": {
239
+ "content": "<box>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": true
245
+ },
246
+ "151673": {
247
+ "content": "</box>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": true
253
+ },
254
+ "151674": {
255
+ "content": "<COMP_CONTEXT>",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": true
261
+ }
262
+ },
263
+ "additional_special_tokens": [
264
+ "<|im_start|>",
265
+ "<|im_end|>",
266
+ "<|object_ref_start|>",
267
+ "<|object_ref_end|>",
268
+ "<|box_start|>",
269
+ "<|box_end|>",
270
+ "<|quad_start|>",
271
+ "<|quad_end|>",
272
+ "<|vision_start|>",
273
+ "<|vision_end|>",
274
+ "<|vision_pad|>",
275
+ "<|image_pad|>",
276
+ "<|video_pad|>"
277
+ ],
278
+ "bos_token": null,
279
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
280
+ "clean_up_tokenization_spaces": false,
281
+ "eos_token": "<|im_end|>",
282
+ "errors": "replace",
283
+ "extra_special_tokens": {},
284
+ "model_max_length": 12288,
285
+ "pad_token": "<|endoftext|>",
286
+ "split_special_tokens": false,
287
+ "tokenizer_class": "Qwen2Tokenizer",
288
+ "unk_token": null
289
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff