Hugging Face's logo

empower-dev-staging
/
internvl-v1-5-v2-gpt-4o

Feature Extraction
Transformers
Safetensors
internvl_chat
custom_code
Model card Files Community
liuylhf commited on
Commit
3ffbe89
•
1 Parent(s): 105c6d3

Upload folder using huggingface_hub

Browse files
Files changed (19) hide show
  1. added_tokens.json +11 -0
  2. config.json +204 -0
  3. generation_config.json +4 -0
  4. model-00001-of-00011.safetensors +3 -0
  5. model-00002-of-00011.safetensors +3 -0
  6. model-00003-of-00011.safetensors +3 -0
  7. model-00004-of-00011.safetensors +3 -0
  8. model-00005-of-00011.safetensors +3 -0
  9. model-00006-of-00011.safetensors +3 -0
  10. model-00007-of-00011.safetensors +3 -0
  11. model-00008-of-00011.safetensors +3 -0
  12. model-00009-of-00011.safetensors +3 -0
  13. model-00010-of-00011.safetensors +3 -0
  14. model-00011-of-00011.safetensors +3 -0
  15. model.safetensors.index.json +941 -0
  16. special_tokens_map.json +41 -0
  17. tokenization_internlm2.py +235 -0
  18. tokenizer.model +3 -0
  19. tokenizer_config.json +173 -0
added_tokens.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 92552,
3
+ "</img>": 92545,
4
+ "</quad>": 92548,
5
+ "</ref>": 92550,
6
+ "<IMG_CONTEXT>": 92546,
7
+ "<box>": 92551,
8
+ "<img>": 92544,
9
+ "<quad>": 92547,
10
+ "<ref>": 92549
11
+ }
config.json ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "work_dirs/InternVL-v1-5-v2-skyvern-v0-gpt-4o",
4
+ "architectures": [
5
+ "InternVLChatModel"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "OpenGVLab/InternVL2-26B--configuration_internvl_chat.InternVLChatConfig",
9
+ "AutoModel": "OpenGVLab/InternVL2-26B--modeling_internvl_chat.InternVLChatModel",
10
+ "AutoModelForCausalLM": "OpenGVLab/InternVL2-26B--modeling_internvl_chat.InternVLChatModel"
11
+ },
12
+ "downsample_ratio": 0.5,
13
+ "dynamic_image_size": true,
14
+ "force_image_size": 448,
15
+ "llm_config": {
16
+ "_name_or_path": "internlm/internlm2-chat-20b",
17
+ "add_cross_attention": false,
18
+ "architectures": [
19
+ "InternLM2ForCausalLM"
20
+ ],
21
+ "attn_implementation": "flash_attention_2",
22
+ "auto_map": {
23
+ "AutoConfig": "configuration_internlm2.InternLM2Config",
24
+ "AutoModel": "modeling_internlm2.InternLM2ForCausalLM",
25
+ "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM"
26
+ },
27
+ "bad_words_ids": null,
28
+ "begin_suppress_tokens": null,
29
+ "bias": false,
30
+ "bos_token_id": 1,
31
+ "chunk_size_feed_forward": 0,
32
+ "cross_attention_hidden_size": null,
33
+ "decoder_start_token_id": null,
34
+ "diversity_penalty": 0.0,
35
+ "do_sample": false,
36
+ "early_stopping": false,
37
+ "encoder_no_repeat_ngram_size": 0,
38
+ "eos_token_id": 2,
39
+ "exponential_decay_length_penalty": null,
40
+ "finetuning_task": null,
41
+ "forced_bos_token_id": null,
42
+ "forced_eos_token_id": null,
43
+ "hidden_act": "silu",
44
+ "hidden_size": 6144,
45
+ "id2label": {
46
+ "0": "LABEL_0",
47
+ "1": "LABEL_1"
48
+ },
49
+ "initializer_range": 0.02,
50
+ "intermediate_size": 16384,
51
+ "is_decoder": false,
52
+ "is_encoder_decoder": false,
53
+ "label2id": {
54
+ "LABEL_0": 0,
55
+ "LABEL_1": 1
56
+ },
57
+ "length_penalty": 1.0,
58
+ "max_length": 20,
59
+ "max_position_embeddings": 32768,
60
+ "min_length": 0,
61
+ "model_type": "internlm2",
62
+ "no_repeat_ngram_size": 0,
63
+ "num_attention_heads": 48,
64
+ "num_beam_groups": 1,
65
+ "num_beams": 1,
66
+ "num_hidden_layers": 48,
67
+ "num_key_value_heads": 8,
68
+ "num_return_sequences": 1,
69
+ "output_attentions": false,
70
+ "output_hidden_states": false,
71
+ "output_scores": false,
72
+ "pad_token_id": 2,
73
+ "prefix": null,
74
+ "problem_type": null,
75
+ "pruned_heads": {},
76
+ "remove_invalid_values": false,
77
+ "repetition_penalty": 1.0,
78
+ "return_dict": true,
79
+ "return_dict_in_generate": false,
80
+ "rms_norm_eps": 1e-05,
81
+ "rope_scaling": {
82
+ "factor": 3.0,
83
+ "type": "dynamic"
84
+ },
85
+ "rope_theta": 1000000,
86
+ "sep_token_id": null,
87
+ "suppress_tokens": null,
88
+ "task_specific_params": null,
89
+ "temperature": 1.0,
90
+ "tf_legacy_loss": false,
91
+ "tie_encoder_decoder": false,
92
+ "tie_word_embeddings": false,
93
+ "tokenizer_class": null,
94
+ "top_k": 50,
95
+ "top_p": 1.0,
96
+ "torch_dtype": "bfloat16",
97
+ "torchscript": false,
98
+ "transformers_version": "4.37.2",
99
+ "typical_p": 1.0,
100
+ "use_bfloat16": true,
101
+ "use_cache": false,
102
+ "vocab_size": 92553
103
+ },
104
+ "max_dynamic_patch": 6,
105
+ "min_dynamic_patch": 1,
106
+ "model_type": "internvl_chat",
107
+ "pad2square": false,
108
+ "ps_version": "v2",
109
+ "select_layer": -1,
110
+ "template": "internlm2-chat",
111
+ "torch_dtype": "bfloat16",
112
+ "transformers_version": null,
113
+ "use_backbone_lora": 0,
114
+ "use_llm_lora": 0,
115
+ "use_thumbnail": true,
116
+ "vision_config": {
117
+ "_name_or_path": "",
118
+ "add_cross_attention": false,
119
+ "architectures": [
120
+ "InternVisionModel"
121
+ ],
122
+ "attention_dropout": 0.0,
123
+ "bad_words_ids": null,
124
+ "begin_suppress_tokens": null,
125
+ "bos_token_id": null,
126
+ "chunk_size_feed_forward": 0,
127
+ "cross_attention_hidden_size": null,
128
+ "decoder_start_token_id": null,
129
+ "diversity_penalty": 0.0,
130
+ "do_sample": false,
131
+ "drop_path_rate": 0,
132
+ "dropout": 0.0,
133
+ "early_stopping": false,
134
+ "encoder_no_repeat_ngram_size": 0,
135
+ "eos_token_id": null,
136
+ "exponential_decay_length_penalty": null,
137
+ "finetuning_task": null,
138
+ "forced_bos_token_id": null,
139
+ "forced_eos_token_id": null,
140
+ "hidden_act": "gelu",
141
+ "hidden_size": 3200,
142
+ "id2label": {
143
+ "0": "LABEL_0",
144
+ "1": "LABEL_1"
145
+ },
146
+ "image_size": 448,
147
+ "initializer_factor": 0.1,
148
+ "initializer_range": 1e-10,
149
+ "intermediate_size": 12800,
150
+ "is_decoder": false,
151
+ "is_encoder_decoder": false,
152
+ "label2id": {
153
+ "LABEL_0": 0,
154
+ "LABEL_1": 1
155
+ },
156
+ "layer_norm_eps": 1e-06,
157
+ "length_penalty": 1.0,
158
+ "max_length": 20,
159
+ "min_length": 0,
160
+ "model_type": "intern_vit_6b",
161
+ "no_repeat_ngram_size": 0,
162
+ "norm_type": "rms_norm",
163
+ "num_attention_heads": 25,
164
+ "num_beam_groups": 1,
165
+ "num_beams": 1,
166
+ "num_channels": 3,
167
+ "num_hidden_layers": 45,
168
+ "num_return_sequences": 1,
169
+ "output_attentions": false,
170
+ "output_hidden_states": false,
171
+ "output_scores": false,
172
+ "pad_token_id": null,
173
+ "patch_size": 14,
174
+ "prefix": null,
175
+ "problem_type": null,
176
+ "pruned_heads": {},
177
+ "qk_normalization": true,
178
+ "qkv_bias": false,
179
+ "remove_invalid_values": false,
180
+ "repetition_penalty": 1.0,
181
+ "return_dict": true,
182
+ "return_dict_in_generate": false,
183
+ "sep_token_id": null,
184
+ "suppress_tokens": null,
185
+ "target_aspect_ratio": [
186
+ 2,
187
+ 1
188
+ ],
189
+ "task_specific_params": null,
190
+ "temperature": 1.0,
191
+ "tf_legacy_loss": false,
192
+ "tie_encoder_decoder": false,
193
+ "tie_word_embeddings": true,
194
+ "tokenizer_class": null,
195
+ "top_k": 50,
196
+ "top_p": 1.0,
197
+ "torch_dtype": "bfloat16",
198
+ "torchscript": false,
199
+ "transformers_version": "4.37.2",
200
+ "typical_p": 1.0,
201
+ "use_bfloat16": true,
202
+ "use_flash_attn": true
203
+ }
204
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.37.2"
4
+ }
model-00001-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43bbb2f1ae6d94ebbe6869a4c45b93cb19a562fe06dfab87fa5340c02c9c2f3d
3
+ size 4988569440
model-00002-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bed4eccf3cffcb860c1c41269c41527a6bef7c9ef6892be8f5d32f74886e075
3
+ size 4937253584
model-00003-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f91358751adfc863740ef05ccc6308f2bda3e7ba56ab37d038d3c93ca26f5f4b
3
+ size 4801189400
model-00004-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d3ebeb39a1c848ccac24e1d3868f834d40e48d95a0616106bf61edac5be148f
3
+ size 4882322840
model-00005-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8be5bbdf48e3d79dcbaa5385642fa532f92170dbfeb2e15527221ea31a06e39c
3
+ size 4882322880
model-00006-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55209a962d87c1fe05e835a01fac7aeaa1935fafcbca30290934ae7b1cdde9dc
3
+ size 4983011128
model-00007-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd5847c7cf8ba6ab54ccbe3d612a3a3366d68a35ef84663e5380a071b8b8122b
3
+ size 4957820488
model-00008-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8938e058bdfc55ad169c171fe4ba14e98193a61fffa354f945cfb94c1f9c4ec4
3
+ size 4882322880
model-00009-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a421a1320ab43442f9bd223f134a87f669f6bb3b2101ef1a2cf0f6d0df5ee156
3
+ size 4983011128
model-00010-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0cc1a06da79e79781e808ea99037a9a0c96745bba9667e0644b4cc741ee9b0b
3
+ size 4957820488
model-00011-of-00011.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4846c9515913be52d0c38e41eec7b4c478ac1f32c17f6142d807426da7b5bb3a
3
+ size 1772842232
model.safetensors.index.json ADDED
@@ -0,0 +1,941 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 51028372224
4
+ },
5
+ "weight_map": {
6
+ "language_model.model.layers.0.attention.wo.weight": "model-00003-of-00011.safetensors",
7
+ "language_model.model.layers.0.attention.wqkv.weight": "model-00003-of-00011.safetensors",
8
+ "language_model.model.layers.0.attention_norm.weight": "model-00003-of-00011.safetensors",
9
+ "language_model.model.layers.0.feed_forward.w1.weight": "model-00003-of-00011.safetensors",
10
+ "language_model.model.layers.0.feed_forward.w2.weight": "model-00003-of-00011.safetensors",
11
+ "language_model.model.layers.0.feed_forward.w3.weight": "model-00003-of-00011.safetensors",
12
+ "language_model.model.layers.0.ffn_norm.weight": "model-00003-of-00011.safetensors",
13
+ "language_model.model.layers.1.attention.wo.weight": "model-00003-of-00011.safetensors",
14
+ "language_model.model.layers.1.attention.wqkv.weight": "model-00003-of-00011.safetensors",
15
+ "language_model.model.layers.1.attention_norm.weight": "model-00003-of-00011.safetensors",
16
+ "language_model.model.layers.1.feed_forward.w1.weight": "model-00003-of-00011.safetensors",
17
+ "language_model.model.layers.1.feed_forward.w2.weight": "model-00003-of-00011.safetensors",
18
+ "language_model.model.layers.1.feed_forward.w3.weight": "model-00003-of-00011.safetensors",
19
+ "language_model.model.layers.1.ffn_norm.weight": "model-00003-of-00011.safetensors",
20
+ "language_model.model.layers.10.attention.wo.weight": "model-00005-of-00011.safetensors",
21
+ "language_model.model.layers.10.attention.wqkv.weight": "model-00005-of-00011.safetensors",
22
+ "language_model.model.layers.10.attention_norm.weight": "model-00005-of-00011.safetensors",
23
+ "language_model.model.layers.10.feed_forward.w1.weight": "model-00005-of-00011.safetensors",
24
+ "language_model.model.layers.10.feed_forward.w2.weight": "model-00005-of-00011.safetensors",
25
+ "language_model.model.layers.10.feed_forward.w3.weight": "model-00005-of-00011.safetensors",
26
+ "language_model.model.layers.10.ffn_norm.weight": "model-00005-of-00011.safetensors",
27
+ "language_model.model.layers.11.attention.wo.weight": "model-00005-of-00011.safetensors",
28
+ "language_model.model.layers.11.attention.wqkv.weight": "model-00005-of-00011.safetensors",
29
+ "language_model.model.layers.11.attention_norm.weight": "model-00005-of-00011.safetensors",
30
+ "language_model.model.layers.11.feed_forward.w1.weight": "model-00005-of-00011.safetensors",
31
+ "language_model.model.layers.11.feed_forward.w2.weight": "model-00005-of-00011.safetensors",
32
+ "language_model.model.layers.11.feed_forward.w3.weight": "model-00005-of-00011.safetensors",
33
+ "language_model.model.layers.11.ffn_norm.weight": "model-00005-of-00011.safetensors",
34
+ "language_model.model.layers.12.attention.wo.weight": "model-00005-of-00011.safetensors",
35
+ "language_model.model.layers.12.attention.wqkv.weight": "model-00005-of-00011.safetensors",
36
+ "language_model.model.layers.12.attention_norm.weight": "model-00005-of-00011.safetensors",
37
+ "language_model.model.layers.12.feed_forward.w1.weight": "model-00005-of-00011.safetensors",
38
+ "language_model.model.layers.12.feed_forward.w2.weight": "model-00005-of-00011.safetensors",
39
+ "language_model.model.layers.12.feed_forward.w3.weight": "model-00005-of-00011.safetensors",
40
+ "language_model.model.layers.12.ffn_norm.weight": "model-00005-of-00011.safetensors",
41
+ "language_model.model.layers.13.attention.wo.weight": "model-00005-of-00011.safetensors",
42
+ "language_model.model.layers.13.attention.wqkv.weight": "model-00005-of-00011.safetensors",
43
+ "language_model.model.layers.13.attention_norm.weight": "model-00005-of-00011.safetensors",
44
+ "language_model.model.layers.13.feed_forward.w1.weight": "model-00005-of-00011.safetensors",
45
+ "language_model.model.layers.13.feed_forward.w2.weight": "model-00005-of-00011.safetensors",
46
+ "language_model.model.layers.13.feed_forward.w3.weight": "model-00005-of-00011.safetensors",
47
+ "language_model.model.layers.13.ffn_norm.weight": "model-00005-of-00011.safetensors",
48
+ "language_model.model.layers.14.attention.wo.weight": "model-00005-of-00011.safetensors",
49
+ "language_model.model.layers.14.attention.wqkv.weight": "model-00005-of-00011.safetensors",
50
+ "language_model.model.layers.14.attention_norm.weight": "model-00005-of-00011.safetensors",
51
+ "language_model.model.layers.14.feed_forward.w1.weight": "model-00005-of-00011.safetensors",
52
+ "language_model.model.layers.14.feed_forward.w2.weight": "model-00005-of-00011.safetensors",
53
+ "language_model.model.layers.14.feed_forward.w3.weight": "model-00005-of-00011.safetensors",
54
+ "language_model.model.layers.14.ffn_norm.weight": "model-00005-of-00011.safetensors",
55
+ "language_model.model.layers.15.attention.wo.weight": "model-00005-of-00011.safetensors",
56
+ "language_model.model.layers.15.attention.wqkv.weight": "model-00005-of-00011.safetensors",
57
+ "language_model.model.layers.15.attention_norm.weight": "model-00006-of-00011.safetensors",
58
+ "language_model.model.layers.15.feed_forward.w1.weight": "model-00005-of-00011.safetensors",
59
+ "language_model.model.layers.15.feed_forward.w2.weight": "model-00006-of-00011.safetensors",
60
+ "language_model.model.layers.15.feed_forward.w3.weight": "model-00005-of-00011.safetensors",
61
+ "language_model.model.layers.15.ffn_norm.weight": "model-00006-of-00011.safetensors",
62
+ "language_model.model.layers.16.attention.wo.weight": "model-00006-of-00011.safetensors",
63
+ "language_model.model.layers.16.attention.wqkv.weight": "model-00006-of-00011.safetensors",
64
+ "language_model.model.layers.16.attention_norm.weight": "model-00006-of-00011.safetensors",
65
+ "language_model.model.layers.16.feed_forward.w1.weight": "model-00006-of-00011.safetensors",
66
+ "language_model.model.layers.16.feed_forward.w2.weight": "model-00006-of-00011.safetensors",
67
+ "language_model.model.layers.16.feed_forward.w3.weight": "model-00006-of-00011.safetensors",
68
+ "language_model.model.layers.16.ffn_norm.weight": "model-00006-of-00011.safetensors",
69
+ "language_model.model.layers.17.attention.wo.weight": "model-00006-of-00011.safetensors",
70
+ "language_model.model.layers.17.attention.wqkv.weight": "model-00006-of-00011.safetensors",
71
+ "language_model.model.layers.17.attention_norm.weight": "model-00006-of-00011.safetensors",
72
+ "language_model.model.layers.17.feed_forward.w1.weight": "model-00006-of-00011.safetensors",
73
+ "language_model.model.layers.17.feed_forward.w2.weight": "model-00006-of-00011.safetensors",
74
+ "language_model.model.layers.17.feed_forward.w3.weight": "model-00006-of-00011.safetensors",
75
+ "language_model.model.layers.17.ffn_norm.weight": "model-00006-of-00011.safetensors",
76
+ "language_model.model.layers.18.attention.wo.weight": "model-00006-of-00011.safetensors",
77
+ "language_model.model.layers.18.attention.wqkv.weight": "model-00006-of-00011.safetensors",
78
+ "language_model.model.layers.18.attention_norm.weight": "model-00006-of-00011.safetensors",
79
+ "language_model.model.layers.18.feed_forward.w1.weight": "model-00006-of-00011.safetensors",
80
+ "language_model.model.layers.18.feed_forward.w2.weight": "model-00006-of-00011.safetensors",
81
+ "language_model.model.layers.18.feed_forward.w3.weight": "model-00006-of-00011.safetensors",
82
+ "language_model.model.layers.18.ffn_norm.weight": "model-00006-of-00011.safetensors",
83
+ "language_model.model.layers.19.attention.wo.weight": "model-00006-of-00011.safetensors",
84
+ "language_model.model.layers.19.attention.wqkv.weight": "model-00006-of-00011.safetensors",
85
+ "language_model.model.layers.19.attention_norm.weight": "model-00006-of-00011.safetensors",
86
+ "language_model.model.layers.19.feed_forward.w1.weight": "model-00006-of-00011.safetensors",
87
+ "language_model.model.layers.19.feed_forward.w2.weight": "model-00006-of-00011.safetensors",
88
+ "language_model.model.layers.19.feed_forward.w3.weight": "model-00006-of-00011.safetensors",
89
+ "language_model.model.layers.19.ffn_norm.weight": "model-00006-of-00011.safetensors",
90
+ "language_model.model.layers.2.attention.wo.weight": "model-00003-of-00011.safetensors",
91
+ "language_model.model.layers.2.attention.wqkv.weight": "model-00003-of-00011.safetensors",
92
+ "language_model.model.layers.2.attention_norm.weight": "model-00003-of-00011.safetensors",
93
+ "language_model.model.layers.2.feed_forward.w1.weight": "model-00003-of-00011.safetensors",
94
+ "language_model.model.layers.2.feed_forward.w2.weight": "model-00003-of-00011.safetensors",
95
+ "language_model.model.layers.2.feed_forward.w3.weight": "model-00003-of-00011.safetensors",
96
+ "language_model.model.layers.2.ffn_norm.weight": "model-00003-of-00011.safetensors",
97
+ "language_model.model.layers.20.attention.wo.weight": "model-00006-of-00011.safetensors",
98
+ "language_model.model.layers.20.attention.wqkv.weight": "model-00006-of-00011.safetensors",
99
+ "language_model.model.layers.20.attention_norm.weight": "model-00006-of-00011.safetensors",
100
+ "language_model.model.layers.20.feed_forward.w1.weight": "model-00006-of-00011.safetensors",
101
+ "language_model.model.layers.20.feed_forward.w2.weight": "model-00006-of-00011.safetensors",
102
+ "language_model.model.layers.20.feed_forward.w3.weight": "model-00006-of-00011.safetensors",
103
+ "language_model.model.layers.20.ffn_norm.weight": "model-00006-of-00011.safetensors",
104
+ "language_model.model.layers.21.attention.wo.weight": "model-00006-of-00011.safetensors",
105
+ "language_model.model.layers.21.attention.wqkv.weight": "model-00006-of-00011.safetensors",
106
+ "language_model.model.layers.21.attention_norm.weight": "model-00006-of-00011.safetensors",
107
+ "language_model.model.layers.21.feed_forward.w1.weight": "model-00006-of-00011.safetensors",
108
+ "language_model.model.layers.21.feed_forward.w2.weight": "model-00006-of-00011.safetensors",
109
+ "language_model.model.layers.21.feed_forward.w3.weight": "model-00006-of-00011.safetensors",
110
+ "language_model.model.layers.21.ffn_norm.weight": "model-00006-of-00011.safetensors",
111
+ "language_model.model.layers.22.attention.wo.weight": "model-00007-of-00011.safetensors",
112
+ "language_model.model.layers.22.attention.wqkv.weight": "model-00006-of-00011.safetensors",
113
+ "language_model.model.layers.22.attention_norm.weight": "model-00007-of-00011.safetensors",
114
+ "language_model.model.layers.22.feed_forward.w1.weight": "model-00007-of-00011.safetensors",
115
+ "language_model.model.layers.22.feed_forward.w2.weight": "model-00007-of-00011.safetensors",
116
+ "language_model.model.layers.22.feed_forward.w3.weight": "model-00007-of-00011.safetensors",
117
+ "language_model.model.layers.22.ffn_norm.weight": "model-00007-of-00011.safetensors",
118
+ "language_model.model.layers.23.attention.wo.weight": "model-00007-of-00011.safetensors",
119
+ "language_model.model.layers.23.attention.wqkv.weight": "model-00007-of-00011.safetensors",
120
+ "language_model.model.layers.23.attention_norm.weight": "model-00007-of-00011.safetensors",
121
+ "language_model.model.layers.23.feed_forward.w1.weight": "model-00007-of-00011.safetensors",
122
+ "language_model.model.layers.23.feed_forward.w2.weight": "model-00007-of-00011.safetensors",
123
+ "language_model.model.layers.23.feed_forward.w3.weight": "model-00007-of-00011.safetensors",
124
+ "language_model.model.layers.23.ffn_norm.weight": "model-00007-of-00011.safetensors",
125
+ "language_model.model.layers.24.attention.wo.weight": "model-00007-of-00011.safetensors",
126
+ "language_model.model.layers.24.attention.wqkv.weight": "model-00007-of-00011.safetensors",
127
+ "language_model.model.layers.24.attention_norm.weight": "model-00007-of-00011.safetensors",
128
+ "language_model.model.layers.24.feed_forward.w1.weight": "model-00007-of-00011.safetensors",
129
+ "language_model.model.layers.24.feed_forward.w2.weight": "model-00007-of-00011.safetensors",
130
+ "language_model.model.layers.24.feed_forward.w3.weight": "model-00007-of-00011.safetensors",
131
+ "language_model.model.layers.24.ffn_norm.weight": "model-00007-of-00011.safetensors",
132
+ "language_model.model.layers.25.attention.wo.weight": "model-00007-of-00011.safetensors",
133
+ "language_model.model.layers.25.attention.wqkv.weight": "model-00007-of-00011.safetensors",
134
+ "language_model.model.layers.25.attention_norm.weight": "model-00007-of-00011.safetensors",
135
+ "language_model.model.layers.25.feed_forward.w1.weight": "model-00007-of-00011.safetensors",
136
+ "language_model.model.layers.25.feed_forward.w2.weight": "model-00007-of-00011.safetensors",
137
+ "language_model.model.layers.25.feed_forward.w3.weight": "model-00007-of-00011.safetensors",
138
+ "language_model.model.layers.25.ffn_norm.weight": "model-00007-of-00011.safetensors",
139
+ "language_model.model.layers.26.attention.wo.weight": "model-00007-of-00011.safetensors",
140
+ "language_model.model.layers.26.attention.wqkv.weight": "model-00007-of-00011.safetensors",
141
+ "language_model.model.layers.26.attention_norm.weight": "model-00007-of-00011.safetensors",
142
+ "language_model.model.layers.26.feed_forward.w1.weight": "model-00007-of-00011.safetensors",
143
+ "language_model.model.layers.26.feed_forward.w2.weight": "model-00007-of-00011.safetensors",
144
+ "language_model.model.layers.26.feed_forward.w3.weight": "model-00007-of-00011.safetensors",
145
+ "language_model.model.layers.26.ffn_norm.weight": "model-00007-of-00011.safetensors",
146
+ "language_model.model.layers.27.attention.wo.weight": "model-00007-of-00011.safetensors",
147
+ "language_model.model.layers.27.attention.wqkv.weight": "model-00007-of-00011.safetensors",
148
+ "language_model.model.layers.27.attention_norm.weight": "model-00007-of-00011.safetensors",
149
+ "language_model.model.layers.27.feed_forward.w1.weight": "model-00007-of-00011.safetensors",
150
+ "language_model.model.layers.27.feed_forward.w2.weight": "model-00007-of-00011.safetensors",
151
+ "language_model.model.layers.27.feed_forward.w3.weight": "model-00007-of-00011.safetensors",
152
+ "language_model.model.layers.27.ffn_norm.weight": "model-00007-of-00011.safetensors",
153
+ "language_model.model.layers.28.attention.wo.weight": "model-00007-of-00011.safetensors",
154
+ "language_model.model.layers.28.attention.wqkv.weight": "model-00007-of-00011.safetensors",
155
+ "language_model.model.layers.28.attention_norm.weight": "model-00008-of-00011.safetensors",
156
+ "language_model.model.layers.28.feed_forward.w1.weight": "model-00007-of-00011.safetensors",
157
+ "language_model.model.layers.28.feed_forward.w2.weight": "model-00008-of-00011.safetensors",
158
+ "language_model.model.layers.28.feed_forward.w3.weight": "model-00008-of-00011.safetensors",
159
+ "language_model.model.layers.28.ffn_norm.weight": "model-00008-of-00011.safetensors",
160
+ "language_model.model.layers.29.attention.wo.weight": "model-00008-of-00011.safetensors",
161
+ "language_model.model.layers.29.attention.wqkv.weight": "model-00008-of-00011.safetensors",
162
+ "language_model.model.layers.29.attention_norm.weight": "model-00008-of-00011.safetensors",
163
+ "language_model.model.layers.29.feed_forward.w1.weight": "model-00008-of-00011.safetensors",
164
+ "language_model.model.layers.29.feed_forward.w2.weight": "model-00008-of-00011.safetensors",
165
+ "language_model.model.layers.29.feed_forward.w3.weight": "model-00008-of-00011.safetensors",
166
+ "language_model.model.layers.29.ffn_norm.weight": "model-00008-of-00011.safetensors",
167
+ "language_model.model.layers.3.attention.wo.weight": "model-00003-of-00011.safetensors",
168
+ "language_model.model.layers.3.attention.wqkv.weight": "model-00003-of-00011.safetensors",
169
+ "language_model.model.layers.3.attention_norm.weight": "model-00004-of-00011.safetensors",
170
+ "language_model.model.layers.3.feed_forward.w1.weight": "model-00004-of-00011.safetensors",
171
+ "language_model.model.layers.3.feed_forward.w2.weight": "model-00004-of-00011.safetensors",
172
+ "language_model.model.layers.3.feed_forward.w3.weight": "model-00004-of-00011.safetensors",
173
+ "language_model.model.layers.3.ffn_norm.weight": "model-00004-of-00011.safetensors",
174
+ "language_model.model.layers.30.attention.wo.weight": "model-00008-of-00011.safetensors",
175
+ "language_model.model.layers.30.attention.wqkv.weight": "model-00008-of-00011.safetensors",
176
+ "language_model.model.layers.30.attention_norm.weight": "model-00008-of-00011.safetensors",
177
+ "language_model.model.layers.30.feed_forward.w1.weight": "model-00008-of-00011.safetensors",
178
+ "language_model.model.layers.30.feed_forward.w2.weight": "model-00008-of-00011.safetensors",
179
+ "language_model.model.layers.30.feed_forward.w3.weight": "model-00008-of-00011.safetensors",
180
+ "language_model.model.layers.30.ffn_norm.weight": "model-00008-of-00011.safetensors",
181
+ "language_model.model.layers.31.attention.wo.weight": "model-00008-of-00011.safetensors",
182
+ "language_model.model.layers.31.attention.wqkv.weight": "model-00008-of-00011.safetensors",
183
+ "language_model.model.layers.31.attention_norm.weight": "model-00008-of-00011.safetensors",
184
+ "language_model.model.layers.31.feed_forward.w1.weight": "model-00008-of-00011.safetensors",
185
+ "language_model.model.layers.31.feed_forward.w2.weight": "model-00008-of-00011.safetensors",
186
+ "language_model.model.layers.31.feed_forward.w3.weight": "model-00008-of-00011.safetensors",
187
+ "language_model.model.layers.31.ffn_norm.weight": "model-00008-of-00011.safetensors",
188
+ "language_model.model.layers.32.attention.wo.weight": "model-00008-of-00011.safetensors",
189
+ "language_model.model.layers.32.attention.wqkv.weight": "model-00008-of-00011.safetensors",
190
+ "language_model.model.layers.32.attention_norm.weight": "model-00008-of-00011.safetensors",
191
+ "language_model.model.layers.32.feed_forward.w1.weight": "model-00008-of-00011.safetensors",
192
+ "language_model.model.layers.32.feed_forward.w2.weight": "model-00008-of-00011.safetensors",
193
+ "language_model.model.layers.32.feed_forward.w3.weight": "model-00008-of-00011.safetensors",
194
+ "language_model.model.layers.32.ffn_norm.weight": "model-00008-of-00011.safetensors",
195
+ "language_model.model.layers.33.attention.wo.weight": "model-00008-of-00011.safetensors",
196
+ "language_model.model.layers.33.attention.wqkv.weight": "model-00008-of-00011.safetensors",
197
+ "language_model.model.layers.33.attention_norm.weight": "model-00008-of-00011.safetensors",
198
+ "language_model.model.layers.33.feed_forward.w1.weight": "model-00008-of-00011.safetensors",
199
+ "language_model.model.layers.33.feed_forward.w2.weight": "model-00008-of-00011.safetensors",
200
+ "language_model.model.layers.33.feed_forward.w3.weight": "model-00008-of-00011.safetensors",
201
+ "language_model.model.layers.33.ffn_norm.weight": "model-00008-of-00011.safetensors",
202
+ "language_model.model.layers.34.attention.wo.weight": "model-00008-of-00011.safetensors",
203
+ "language_model.model.layers.34.attention.wqkv.weight": "model-00008-of-00011.safetensors",
204
+ "language_model.model.layers.34.attention_norm.weight": "model-00009-of-00011.safetensors",
205
+ "language_model.model.layers.34.feed_forward.w1.weight": "model-00008-of-00011.safetensors",
206
+ "language_model.model.layers.34.feed_forward.w2.weight": "model-00009-of-00011.safetensors",
207
+ "language_model.model.layers.34.feed_forward.w3.weight": "model-00008-of-00011.safetensors",
208
+ "language_model.model.layers.34.ffn_norm.weight": "model-00009-of-00011.safetensors",
209
+ "language_model.model.layers.35.attention.wo.weight": "model-00009-of-00011.safetensors",
210
+ "language_model.model.layers.35.attention.wqkv.weight": "model-00009-of-00011.safetensors",
211
+ "language_model.model.layers.35.attention_norm.weight": "model-00009-of-00011.safetensors",
212
+ "language_model.model.layers.35.feed_forward.w1.weight": "model-00009-of-00011.safetensors",
213
+ "language_model.model.layers.35.feed_forward.w2.weight": "model-00009-of-00011.safetensors",
214
+ "language_model.model.layers.35.feed_forward.w3.weight": "model-00009-of-00011.safetensors",
215
+ "language_model.model.layers.35.ffn_norm.weight": "model-00009-of-00011.safetensors",
216
+ "language_model.model.layers.36.attention.wo.weight": "model-00009-of-00011.safetensors",
217
+ "language_model.model.layers.36.attention.wqkv.weight": "model-00009-of-00011.safetensors",
218
+ "language_model.model.layers.36.attention_norm.weight": "model-00009-of-00011.safetensors",
219
+ "language_model.model.layers.36.feed_forward.w1.weight": "model-00009-of-00011.safetensors",
220
+ "language_model.model.layers.36.feed_forward.w2.weight": "model-00009-of-00011.safetensors",
221
+ "language_model.model.layers.36.feed_forward.w3.weight": "model-00009-of-00011.safetensors",
222
+ "language_model.model.layers.36.ffn_norm.weight": "model-00009-of-00011.safetensors",
223
+ "language_model.model.layers.37.attention.wo.weight": "model-00009-of-00011.safetensors",
224
+ "language_model.model.layers.37.attention.wqkv.weight": "model-00009-of-00011.safetensors",
225
+ "language_model.model.layers.37.attention_norm.weight": "model-00009-of-00011.safetensors",
226
+ "language_model.model.layers.37.feed_forward.w1.weight": "model-00009-of-00011.safetensors",
227
+ "language_model.model.layers.37.feed_forward.w2.weight": "model-00009-of-00011.safetensors",
228
+ "language_model.model.layers.37.feed_forward.w3.weight": "model-00009-of-00011.safetensors",
229
+ "language_model.model.layers.37.ffn_norm.weight": "model-00009-of-00011.safetensors",
230
+ "language_model.model.layers.38.attention.wo.weight": "model-00009-of-00011.safetensors",
231
+ "language_model.model.layers.38.attention.wqkv.weight": "model-00009-of-00011.safetensors",
232
+ "language_model.model.layers.38.attention_norm.weight": "model-00009-of-00011.safetensors",
233
+ "language_model.model.layers.38.feed_forward.w1.weight": "model-00009-of-00011.safetensors",
234
+ "language_model.model.layers.38.feed_forward.w2.weight": "model-00009-of-00011.safetensors",
235
+ "language_model.model.layers.38.feed_forward.w3.weight": "model-00009-of-00011.safetensors",
236
+ "language_model.model.layers.38.ffn_norm.weight": "model-00009-of-00011.safetensors",
237
+ "language_model.model.layers.39.attention.wo.weight": "model-00009-of-00011.safetensors",
238
+ "language_model.model.layers.39.attention.wqkv.weight": "model-00009-of-00011.safetensors",
239
+ "language_model.model.layers.39.attention_norm.weight": "model-00009-of-00011.safetensors",
240
+ "language_model.model.layers.39.feed_forward.w1.weight": "model-00009-of-00011.safetensors",
241
+ "language_model.model.layers.39.feed_forward.w2.weight": "model-00009-of-00011.safetensors",
242
+ "language_model.model.layers.39.feed_forward.w3.weight": "model-00009-of-00011.safetensors",
243
+ "language_model.model.layers.39.ffn_norm.weight": "model-00009-of-00011.safetensors",
244
+ "language_model.model.layers.4.attention.wo.weight": "model-00004-of-00011.safetensors",
245
+ "language_model.model.layers.4.attention.wqkv.weight": "model-00004-of-00011.safetensors",
246
+ "language_model.model.layers.4.attention_norm.weight": "model-00004-of-00011.safetensors",
247
+ "language_model.model.layers.4.feed_forward.w1.weight": "model-00004-of-00011.safetensors",
248
+ "language_model.model.layers.4.feed_forward.w2.weight": "model-00004-of-00011.safetensors",
249
+ "language_model.model.layers.4.feed_forward.w3.weight": "model-00004-of-00011.safetensors",
250
+ "language_model.model.layers.4.ffn_norm.weight": "model-00004-of-00011.safetensors",
251
+ "language_model.model.layers.40.attention.wo.weight": "model-00009-of-00011.safetensors",
252
+ "language_model.model.layers.40.attention.wqkv.weight": "model-00009-of-00011.safetensors",
253
+ "language_model.model.layers.40.attention_norm.weight": "model-00009-of-00011.safetensors",
254
+ "language_model.model.layers.40.feed_forward.w1.weight": "model-00009-of-00011.safetensors",
255
+ "language_model.model.layers.40.feed_forward.w2.weight": "model-00009-of-00011.safetensors",
256
+ "language_model.model.layers.40.feed_forward.w3.weight": "model-00009-of-00011.safetensors",
257
+ "language_model.model.layers.40.ffn_norm.weight": "model-00009-of-00011.safetensors",
258
+ "language_model.model.layers.41.attention.wo.weight": "model-00010-of-00011.safetensors",
259
+ "language_model.model.layers.41.attention.wqkv.weight": "model-00009-of-00011.safetensors",
260
+ "language_model.model.layers.41.attention_norm.weight": "model-00010-of-00011.safetensors",
261
+ "language_model.model.layers.41.feed_forward.w1.weight": "model-00010-of-00011.safetensors",
262
+ "language_model.model.layers.41.feed_forward.w2.weight": "model-00010-of-00011.safetensors",
263
+ "language_model.model.layers.41.feed_forward.w3.weight": "model-00010-of-00011.safetensors",
264
+ "language_model.model.layers.41.ffn_norm.weight": "model-00010-of-00011.safetensors",
265
+ "language_model.model.layers.42.attention.wo.weight": "model-00010-of-00011.safetensors",
266
+ "language_model.model.layers.42.attention.wqkv.weight": "model-00010-of-00011.safetensors",
267
+ "language_model.model.layers.42.attention_norm.weight": "model-00010-of-00011.safetensors",
268
+ "language_model.model.layers.42.feed_forward.w1.weight": "model-00010-of-00011.safetensors",
269
+ "language_model.model.layers.42.feed_forward.w2.weight": "model-00010-of-00011.safetensors",
270
+ "language_model.model.layers.42.feed_forward.w3.weight": "model-00010-of-00011.safetensors",
271
+ "language_model.model.layers.42.ffn_norm.weight": "model-00010-of-00011.safetensors",
272
+ "language_model.model.layers.43.attention.wo.weight": "model-00010-of-00011.safetensors",
273
+ "language_model.model.layers.43.attention.wqkv.weight": "model-00010-of-00011.safetensors",
274
+ "language_model.model.layers.43.attention_norm.weight": "model-00010-of-00011.safetensors",
275
+ "language_model.model.layers.43.feed_forward.w1.weight": "model-00010-of-00011.safetensors",
276
+ "language_model.model.layers.43.feed_forward.w2.weight": "model-00010-of-00011.safetensors",
277
+ "language_model.model.layers.43.feed_forward.w3.weight": "model-00010-of-00011.safetensors",
278
+ "language_model.model.layers.43.ffn_norm.weight": "model-00010-of-00011.safetensors",
279
+ "language_model.model.layers.44.attention.wo.weight": "model-00010-of-00011.safetensors",
280
+ "language_model.model.layers.44.attention.wqkv.weight": "model-00010-of-00011.safetensors",
281
+ "language_model.model.layers.44.attention_norm.weight": "model-00010-of-00011.safetensors",
282
+ "language_model.model.layers.44.feed_forward.w1.weight": "model-00010-of-00011.safetensors",
283
+ "language_model.model.layers.44.feed_forward.w2.weight": "model-00010-of-00011.safetensors",
284
+ "language_model.model.layers.44.feed_forward.w3.weight": "model-00010-of-00011.safetensors",
285
+ "language_model.model.layers.44.ffn_norm.weight": "model-00010-of-00011.safetensors",
286
+ "language_model.model.layers.45.attention.wo.weight": "model-00010-of-00011.safetensors",
287
+ "language_model.model.layers.45.attention.wqkv.weight": "model-00010-of-00011.safetensors",
288
+ "language_model.model.layers.45.attention_norm.weight": "model-00010-of-00011.safetensors",
289
+ "language_model.model.layers.45.feed_forward.w1.weight": "model-00010-of-00011.safetensors",
290
+ "language_model.model.layers.45.feed_forward.w2.weight": "model-00010-of-00011.safetensors",
291
+ "language_model.model.layers.45.feed_forward.w3.weight": "model-00010-of-00011.safetensors",
292
+ "language_model.model.layers.45.ffn_norm.weight": "model-00010-of-00011.safetensors",
293
+ "language_model.model.layers.46.attention.wo.weight": "model-00010-of-00011.safetensors",
294
+ "language_model.model.layers.46.attention.wqkv.weight": "model-00010-of-00011.safetensors",
295
+ "language_model.model.layers.46.attention_norm.weight": "model-00010-of-00011.safetensors",
296
+ "language_model.model.layers.46.feed_forward.w1.weight": "model-00010-of-00011.safetensors",
297
+ "language_model.model.layers.46.feed_forward.w2.weight": "model-00010-of-00011.safetensors",
298
+ "language_model.model.layers.46.feed_forward.w3.weight": "model-00010-of-00011.safetensors",
299
+ "language_model.model.layers.46.ffn_norm.weight": "model-00010-of-00011.safetensors",
300
+ "language_model.model.layers.47.attention.wo.weight": "model-00010-of-00011.safetensors",
301
+ "language_model.model.layers.47.attention.wqkv.weight": "model-00010-of-00011.safetensors",
302
+ "language_model.model.layers.47.attention_norm.weight": "model-00011-of-00011.safetensors",
303
+ "language_model.model.layers.47.feed_forward.w1.weight": "model-00010-of-00011.safetensors",
304
+ "language_model.model.layers.47.feed_forward.w2.weight": "model-00011-of-00011.safetensors",
305
+ "language_model.model.layers.47.feed_forward.w3.weight": "model-00011-of-00011.safetensors",
306
+ "language_model.model.layers.47.ffn_norm.weight": "model-00011-of-00011.safetensors",
307
+ "language_model.model.layers.5.attention.wo.weight": "model-00004-of-00011.safetensors",
308
+ "language_model.model.layers.5.attention.wqkv.weight": "model-00004-of-00011.safetensors",
309
+ "language_model.model.layers.5.attention_norm.weight": "model-00004-of-00011.safetensors",
310
+ "language_model.model.layers.5.feed_forward.w1.weight": "model-00004-of-00011.safetensors",
311
+ "language_model.model.layers.5.feed_forward.w2.weight": "model-00004-of-00011.safetensors",
312
+ "language_model.model.layers.5.feed_forward.w3.weight": "model-00004-of-00011.safetensors",
313
+ "language_model.model.layers.5.ffn_norm.weight": "model-00004-of-00011.safetensors",
314
+ "language_model.model.layers.6.attention.wo.weight": "model-00004-of-00011.safetensors",
315
+ "language_model.model.layers.6.attention.wqkv.weight": "model-00004-of-00011.safetensors",
316
+ "language_model.model.layers.6.attention_norm.weight": "model-00004-of-00011.safetensors",
317
+ "language_model.model.layers.6.feed_forward.w1.weight": "model-00004-of-00011.safetensors",
318
+ "language_model.model.layers.6.feed_forward.w2.weight": "model-00004-of-00011.safetensors",
319
+ "language_model.model.layers.6.feed_forward.w3.weight": "model-00004-of-00011.safetensors",
320
+ "language_model.model.layers.6.ffn_norm.weight": "model-00004-of-00011.safetensors",
321
+ "language_model.model.layers.7.attention.wo.weight": "model-00004-of-00011.safetensors",
322
+ "language_model.model.layers.7.attention.wqkv.weight": "model-00004-of-00011.safetensors",
323
+ "language_model.model.layers.7.attention_norm.weight": "model-00004-of-00011.safetensors",
324
+ "language_model.model.layers.7.feed_forward.w1.weight": "model-00004-of-00011.safetensors",
325
+ "language_model.model.layers.7.feed_forward.w2.weight": "model-00004-of-00011.safetensors",
326
+ "language_model.model.layers.7.feed_forward.w3.weight": "model-00004-of-00011.safetensors",
327
+ "language_model.model.layers.7.ffn_norm.weight": "model-00004-of-00011.safetensors",
328
+ "language_model.model.layers.8.attention.wo.weight": "model-00004-of-00011.safetensors",
329
+ "language_model.model.layers.8.attention.wqkv.weight": "model-00004-of-00011.safetensors",
330
+ "language_model.model.layers.8.attention_norm.weight": "model-00004-of-00011.safetensors",
331
+ "language_model.model.layers.8.feed_forward.w1.weight": "model-00004-of-00011.safetensors",
332
+ "language_model.model.layers.8.feed_forward.w2.weight": "model-00004-of-00011.safetensors",
333
+ "language_model.model.layers.8.feed_forward.w3.weight": "model-00004-of-00011.safetensors",
334
+ "language_model.model.layers.8.ffn_norm.weight": "model-00004-of-00011.safetensors",
335
+ "language_model.model.layers.9.attention.wo.weight": "model-00004-of-00011.safetensors",
336
+ "language_model.model.layers.9.attention.wqkv.weight": "model-00004-of-00011.safetensors",
337
+ "language_model.model.layers.9.attention_norm.weight": "model-00005-of-00011.safetensors",
338
+ "language_model.model.layers.9.feed_forward.w1.weight": "model-00004-of-00011.safetensors",
339
+ "language_model.model.layers.9.feed_forward.w2.weight": "model-00005-of-00011.safetensors",
340
+ "language_model.model.layers.9.feed_forward.w3.weight": "model-00005-of-00011.safetensors",
341
+ "language_model.model.layers.9.ffn_norm.weight": "model-00005-of-00011.safetensors",
342
+ "language_model.model.norm.weight": "model-00011-of-00011.safetensors",
343
+ "language_model.model.tok_embeddings.weight": "model-00003-of-00011.safetensors",
344
+ "language_model.output.weight": "model-00011-of-00011.safetensors",
345
+ "mlp1.0.bias": "model-00011-of-00011.safetensors",
346
+ "mlp1.0.weight": "model-00011-of-00011.safetensors",
347
+ "mlp1.1.bias": "model-00011-of-00011.safetensors",
348
+ "mlp1.1.weight": "model-00011-of-00011.safetensors",
349
+ "mlp1.3.bias": "model-00011-of-00011.safetensors",
350
+ "mlp1.3.weight": "model-00011-of-00011.safetensors",
351
+ "vision_model.embeddings.class_embedding": "model-00001-of-00011.safetensors",
352
+ "vision_model.embeddings.patch_embedding.bias": "model-00001-of-00011.safetensors",
353
+ "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00011.safetensors",
354
+ "vision_model.embeddings.position_embedding": "model-00001-of-00011.safetensors",
355
+ "vision_model.encoder.layers.0.attn.k_norm.weight": "model-00001-of-00011.safetensors",
356
+ "vision_model.encoder.layers.0.attn.proj.bias": "model-00001-of-00011.safetensors",
357
+ "vision_model.encoder.layers.0.attn.proj.weight": "model-00001-of-00011.safetensors",
358
+ "vision_model.encoder.layers.0.attn.q_norm.weight": "model-00001-of-00011.safetensors",
359
+ "vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00011.safetensors",
360
+ "vision_model.encoder.layers.0.ls1": "model-00001-of-00011.safetensors",
361
+ "vision_model.encoder.layers.0.ls2": "model-00001-of-00011.safetensors",
362
+ "vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00011.safetensors",
363
+ "vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00011.safetensors",
364
+ "vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00011.safetensors",
365
+ "vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00011.safetensors",
366
+ "vision_model.encoder.layers.0.norm1.weight": "model-00001-of-00011.safetensors",
367
+ "vision_model.encoder.layers.0.norm2.weight": "model-00001-of-00011.safetensors",
368
+ "vision_model.encoder.layers.1.attn.k_norm.weight": "model-00001-of-00011.safetensors",
369
+ "vision_model.encoder.layers.1.attn.proj.bias": "model-00001-of-00011.safetensors",
370
+ "vision_model.encoder.layers.1.attn.proj.weight": "model-00001-of-00011.safetensors",
371
+ "vision_model.encoder.layers.1.attn.q_norm.weight": "model-00001-of-00011.safetensors",
372
+ "vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00011.safetensors",
373
+ "vision_model.encoder.layers.1.ls1": "model-00001-of-00011.safetensors",
374
+ "vision_model.encoder.layers.1.ls2": "model-00001-of-00011.safetensors",
375
+ "vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00011.safetensors",
376
+ "vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00011.safetensors",
377
+ "vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00011.safetensors",
378
+ "vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00011.safetensors",
379
+ "vision_model.encoder.layers.1.norm1.weight": "model-00001-of-00011.safetensors",
380
+ "vision_model.encoder.layers.1.norm2.weight": "model-00001-of-00011.safetensors",
381
+ "vision_model.encoder.layers.10.attn.k_norm.weight": "model-00001-of-00011.safetensors",
382
+ "vision_model.encoder.layers.10.attn.proj.bias": "model-00001-of-00011.safetensors",
383
+ "vision_model.encoder.layers.10.attn.proj.weight": "model-00001-of-00011.safetensors",
384
+ "vision_model.encoder.layers.10.attn.q_norm.weight": "model-00001-of-00011.safetensors",
385
+ "vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00011.safetensors",
386
+ "vision_model.encoder.layers.10.ls1": "model-00001-of-00011.safetensors",
387
+ "vision_model.encoder.layers.10.ls2": "model-00001-of-00011.safetensors",
388
+ "vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00011.safetensors",
389
+ "vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00011.safetensors",
390
+ "vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00011.safetensors",
391
+ "vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00011.safetensors",
392
+ "vision_model.encoder.layers.10.norm1.weight": "model-00001-of-00011.safetensors",
393
+ "vision_model.encoder.layers.10.norm2.weight": "model-00001-of-00011.safetensors",
394
+ "vision_model.encoder.layers.11.attn.k_norm.weight": "model-00001-of-00011.safetensors",
395
+ "vision_model.encoder.layers.11.attn.proj.bias": "model-00001-of-00011.safetensors",
396
+ "vision_model.encoder.layers.11.attn.proj.weight": "model-00001-of-00011.safetensors",
397
+ "vision_model.encoder.layers.11.attn.q_norm.weight": "model-00001-of-00011.safetensors",
398
+ "vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00011.safetensors",
399
+ "vision_model.encoder.layers.11.ls1": "model-00001-of-00011.safetensors",
400
+ "vision_model.encoder.layers.11.ls2": "model-00001-of-00011.safetensors",
401
+ "vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00011.safetensors",
402
+ "vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00011.safetensors",
403
+ "vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00011.safetensors",
404
+ "vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00011.safetensors",
405
+ "vision_model.encoder.layers.11.norm1.weight": "model-00001-of-00011.safetensors",
406
+ "vision_model.encoder.layers.11.norm2.weight": "model-00001-of-00011.safetensors",
407
+ "vision_model.encoder.layers.12.attn.k_norm.weight": "model-00001-of-00011.safetensors",
408
+ "vision_model.encoder.layers.12.attn.proj.bias": "model-00001-of-00011.safetensors",
409
+ "vision_model.encoder.layers.12.attn.proj.weight": "model-00001-of-00011.safetensors",
410
+ "vision_model.encoder.layers.12.attn.q_norm.weight": "model-00001-of-00011.safetensors",
411
+ "vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00011.safetensors",
412
+ "vision_model.encoder.layers.12.ls1": "model-00001-of-00011.safetensors",
413
+ "vision_model.encoder.layers.12.ls2": "model-00001-of-00011.safetensors",
414
+ "vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00011.safetensors",
415
+ "vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00011.safetensors",
416
+ "vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00011.safetensors",
417
+ "vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00011.safetensors",
418
+ "vision_model.encoder.layers.12.norm1.weight": "model-00001-of-00011.safetensors",
419
+ "vision_model.encoder.layers.12.norm2.weight": "model-00001-of-00011.safetensors",
420
+ "vision_model.encoder.layers.13.attn.k_norm.weight": "model-00001-of-00011.safetensors",
421
+ "vision_model.encoder.layers.13.attn.proj.bias": "model-00001-of-00011.safetensors",
422
+ "vision_model.encoder.layers.13.attn.proj.weight": "model-00001-of-00011.safetensors",
423
+ "vision_model.encoder.layers.13.attn.q_norm.weight": "model-00001-of-00011.safetensors",
424
+ "vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00011.safetensors",
425
+ "vision_model.encoder.layers.13.ls1": "model-00001-of-00011.safetensors",
426
+ "vision_model.encoder.layers.13.ls2": "model-00001-of-00011.safetensors",
427
+ "vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00011.safetensors",
428
+ "vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00011.safetensors",
429
+ "vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00011.safetensors",
430
+ "vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00011.safetensors",
431
+ "vision_model.encoder.layers.13.norm1.weight": "model-00001-of-00011.safetensors",
432
+ "vision_model.encoder.layers.13.norm2.weight": "model-00001-of-00011.safetensors",
433
+ "vision_model.encoder.layers.14.attn.k_norm.weight": "model-00001-of-00011.safetensors",
434
+ "vision_model.encoder.layers.14.attn.proj.bias": "model-00001-of-00011.safetensors",
435
+ "vision_model.encoder.layers.14.attn.proj.weight": "model-00001-of-00011.safetensors",
436
+ "vision_model.encoder.layers.14.attn.q_norm.weight": "model-00001-of-00011.safetensors",
437
+ "vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00011.safetensors",
438
+ "vision_model.encoder.layers.14.ls1": "model-00001-of-00011.safetensors",
439
+ "vision_model.encoder.layers.14.ls2": "model-00001-of-00011.safetensors",
440
+ "vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00011.safetensors",
441
+ "vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00011.safetensors",
442
+ "vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00011.safetensors",
443
+ "vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00011.safetensors",
444
+ "vision_model.encoder.layers.14.norm1.weight": "model-00001-of-00011.safetensors",
445
+ "vision_model.encoder.layers.14.norm2.weight": "model-00001-of-00011.safetensors",
446
+ "vision_model.encoder.layers.15.attn.k_norm.weight": "model-00001-of-00011.safetensors",
447
+ "vision_model.encoder.layers.15.attn.proj.bias": "model-00001-of-00011.safetensors",
448
+ "vision_model.encoder.layers.15.attn.proj.weight": "model-00001-of-00011.safetensors",
449
+ "vision_model.encoder.layers.15.attn.q_norm.weight": "model-00001-of-00011.safetensors",
450
+ "vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00011.safetensors",
451
+ "vision_model.encoder.layers.15.ls1": "model-00001-of-00011.safetensors",
452
+ "vision_model.encoder.layers.15.ls2": "model-00001-of-00011.safetensors",
453
+ "vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00011.safetensors",
454
+ "vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00011.safetensors",
455
+ "vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00011.safetensors",
456
+ "vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00011.safetensors",
457
+ "vision_model.encoder.layers.15.norm1.weight": "model-00001-of-00011.safetensors",
458
+ "vision_model.encoder.layers.15.norm2.weight": "model-00001-of-00011.safetensors",
459
+ "vision_model.encoder.layers.16.attn.k_norm.weight": "model-00001-of-00011.safetensors",
460
+ "vision_model.encoder.layers.16.attn.proj.bias": "model-00001-of-00011.safetensors",
461
+ "vision_model.encoder.layers.16.attn.proj.weight": "model-00001-of-00011.safetensors",
462
+ "vision_model.encoder.layers.16.attn.q_norm.weight": "model-00001-of-00011.safetensors",
463
+ "vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00011.safetensors",
464
+ "vision_model.encoder.layers.16.ls1": "model-00001-of-00011.safetensors",
465
+ "vision_model.encoder.layers.16.ls2": "model-00001-of-00011.safetensors",
466
+ "vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00011.safetensors",
467
+ "vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00011.safetensors",
468
+ "vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00011.safetensors",
469
+ "vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00011.safetensors",
470
+ "vision_model.encoder.layers.16.norm1.weight": "model-00001-of-00011.safetensors",
471
+ "vision_model.encoder.layers.16.norm2.weight": "model-00001-of-00011.safetensors",
472
+ "vision_model.encoder.layers.17.attn.k_norm.weight": "model-00001-of-00011.safetensors",
473
+ "vision_model.encoder.layers.17.attn.proj.bias": "model-00001-of-00011.safetensors",
474
+ "vision_model.encoder.layers.17.attn.proj.weight": "model-00001-of-00011.safetensors",
475
+ "vision_model.encoder.layers.17.attn.q_norm.weight": "model-00001-of-00011.safetensors",
476
+ "vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00011.safetensors",
477
+ "vision_model.encoder.layers.17.ls1": "model-00001-of-00011.safetensors",
478
+ "vision_model.encoder.layers.17.ls2": "model-00001-of-00011.safetensors",
479
+ "vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00011.safetensors",
480
+ "vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00011.safetensors",
481
+ "vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00011.safetensors",
482
+ "vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00011.safetensors",
483
+ "vision_model.encoder.layers.17.norm1.weight": "model-00001-of-00011.safetensors",
484
+ "vision_model.encoder.layers.17.norm2.weight": "model-00001-of-00011.safetensors",
485
+ "vision_model.encoder.layers.18.attn.k_norm.weight": "model-00001-of-00011.safetensors",
486
+ "vision_model.encoder.layers.18.attn.proj.bias": "model-00001-of-00011.safetensors",
487
+ "vision_model.encoder.layers.18.attn.proj.weight": "model-00001-of-00011.safetensors",
488
+ "vision_model.encoder.layers.18.attn.q_norm.weight": "model-00001-of-00011.safetensors",
489
+ "vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00011.safetensors",
490
+ "vision_model.encoder.layers.18.ls1": "model-00001-of-00011.safetensors",
491
+ "vision_model.encoder.layers.18.ls2": "model-00001-of-00011.safetensors",
492
+ "vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00011.safetensors",
493
+ "vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00011.safetensors",
494
+ "vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00011.safetensors",
495
+ "vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00011.safetensors",
496
+ "vision_model.encoder.layers.18.norm1.weight": "model-00001-of-00011.safetensors",
497
+ "vision_model.encoder.layers.18.norm2.weight": "model-00001-of-00011.safetensors",
498
+ "vision_model.encoder.layers.19.attn.k_norm.weight": "model-00001-of-00011.safetensors",
499
+ "vision_model.encoder.layers.19.attn.proj.bias": "model-00001-of-00011.safetensors",
500
+ "vision_model.encoder.layers.19.attn.proj.weight": "model-00001-of-00011.safetensors",
501
+ "vision_model.encoder.layers.19.attn.q_norm.weight": "model-00001-of-00011.safetensors",
502
+ "vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00011.safetensors",
503
+ "vision_model.encoder.layers.19.ls1": "model-00001-of-00011.safetensors",
504
+ "vision_model.encoder.layers.19.ls2": "model-00001-of-00011.safetensors",
505
+ "vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00011.safetensors",
506
+ "vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00011.safetensors",
507
+ "vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00011.safetensors",
508
+ "vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00011.safetensors",
509
+ "vision_model.encoder.layers.19.norm1.weight": "model-00001-of-00011.safetensors",
510
+ "vision_model.encoder.layers.19.norm2.weight": "model-00001-of-00011.safetensors",
511
+ "vision_model.encoder.layers.2.attn.k_norm.weight": "model-00001-of-00011.safetensors",
512
+ "vision_model.encoder.layers.2.attn.proj.bias": "model-00001-of-00011.safetensors",
513
+ "vision_model.encoder.layers.2.attn.proj.weight": "model-00001-of-00011.safetensors",
514
+ "vision_model.encoder.layers.2.attn.q_norm.weight": "model-00001-of-00011.safetensors",
515
+ "vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00011.safetensors",
516
+ "vision_model.encoder.layers.2.ls1": "model-00001-of-00011.safetensors",
517
+ "vision_model.encoder.layers.2.ls2": "model-00001-of-00011.safetensors",
518
+ "vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00011.safetensors",
519
+ "vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00011.safetensors",
520
+ "vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00011.safetensors",
521
+ "vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00011.safetensors",
522
+ "vision_model.encoder.layers.2.norm1.weight": "model-00001-of-00011.safetensors",
523
+ "vision_model.encoder.layers.2.norm2.weight": "model-00001-of-00011.safetensors",
524
+ "vision_model.encoder.layers.20.attn.k_norm.weight": "model-00001-of-00011.safetensors",
525
+ "vision_model.encoder.layers.20.attn.proj.bias": "model-00002-of-00011.safetensors",
526
+ "vision_model.encoder.layers.20.attn.proj.weight": "model-00002-of-00011.safetensors",
527
+ "vision_model.encoder.layers.20.attn.q_norm.weight": "model-00001-of-00011.safetensors",
528
+ "vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00011.safetensors",
529
+ "vision_model.encoder.layers.20.ls1": "model-00001-of-00011.safetensors",
530
+ "vision_model.encoder.layers.20.ls2": "model-00001-of-00011.safetensors",
531
+ "vision_model.encoder.layers.20.mlp.fc1.bias": "model-00002-of-00011.safetensors",
532
+ "vision_model.encoder.layers.20.mlp.fc1.weight": "model-00002-of-00011.safetensors",
533
+ "vision_model.encoder.layers.20.mlp.fc2.bias": "model-00002-of-00011.safetensors",
534
+ "vision_model.encoder.layers.20.mlp.fc2.weight": "model-00002-of-00011.safetensors",
535
+ "vision_model.encoder.layers.20.norm1.weight": "model-00002-of-00011.safetensors",
536
+ "vision_model.encoder.layers.20.norm2.weight": "model-00002-of-00011.safetensors",
537
+ "vision_model.encoder.layers.21.attn.k_norm.weight": "model-00002-of-00011.safetensors",
538
+ "vision_model.encoder.layers.21.attn.proj.bias": "model-00002-of-00011.safetensors",
539
+ "vision_model.encoder.layers.21.attn.proj.weight": "model-00002-of-00011.safetensors",
540
+ "vision_model.encoder.layers.21.attn.q_norm.weight": "model-00002-of-00011.safetensors",
541
+ "vision_model.encoder.layers.21.attn.qkv.weight": "model-00002-of-00011.safetensors",
542
+ "vision_model.encoder.layers.21.ls1": "model-00002-of-00011.safetensors",
543
+ "vision_model.encoder.layers.21.ls2": "model-00002-of-00011.safetensors",
544
+ "vision_model.encoder.layers.21.mlp.fc1.bias": "model-00002-of-00011.safetensors",
545
+ "vision_model.encoder.layers.21.mlp.fc1.weight": "model-00002-of-00011.safetensors",
546
+ "vision_model.encoder.layers.21.mlp.fc2.bias": "model-00002-of-00011.safetensors",
547
+ "vision_model.encoder.layers.21.mlp.fc2.weight": "model-00002-of-00011.safetensors",
548
+ "vision_model.encoder.layers.21.norm1.weight": "model-00002-of-00011.safetensors",
549
+ "vision_model.encoder.layers.21.norm2.weight": "model-00002-of-00011.safetensors",
550
+ "vision_model.encoder.layers.22.attn.k_norm.weight": "model-00002-of-00011.safetensors",
551
+ "vision_model.encoder.layers.22.attn.proj.bias": "model-00002-of-00011.safetensors",
552
+ "vision_model.encoder.layers.22.attn.proj.weight": "model-00002-of-00011.safetensors",
553
+ "vision_model.encoder.layers.22.attn.q_norm.weight": "model-00002-of-00011.safetensors",
554
+ "vision_model.encoder.layers.22.attn.qkv.weight": "model-00002-of-00011.safetensors",
555
+ "vision_model.encoder.layers.22.ls1": "model-00002-of-00011.safetensors",
556
+ "vision_model.encoder.layers.22.ls2": "model-00002-of-00011.safetensors",
557
+ "vision_model.encoder.layers.22.mlp.fc1.bias": "model-00002-of-00011.safetensors",
558
+ "vision_model.encoder.layers.22.mlp.fc1.weight": "model-00002-of-00011.safetensors",
559
+ "vision_model.encoder.layers.22.mlp.fc2.bias": "model-00002-of-00011.safetensors",
560
+ "vision_model.encoder.layers.22.mlp.fc2.weight": "model-00002-of-00011.safetensors",
561
+ "vision_model.encoder.layers.22.norm1.weight": "model-00002-of-00011.safetensors",
562
+ "vision_model.encoder.layers.22.norm2.weight": "model-00002-of-00011.safetensors",
563
+ "vision_model.encoder.layers.23.attn.k_norm.weight": "model-00002-of-00011.safetensors",
564
+ "vision_model.encoder.layers.23.attn.proj.bias": "model-00002-of-00011.safetensors",
565
+ "vision_model.encoder.layers.23.attn.proj.weight": "model-00002-of-00011.safetensors",
566
+ "vision_model.encoder.layers.23.attn.q_norm.weight": "model-00002-of-00011.safetensors",
567
+ "vision_model.encoder.layers.23.attn.qkv.weight": "model-00002-of-00011.safetensors",
568
+ "vision_model.encoder.layers.23.ls1": "model-00002-of-00011.safetensors",
569
+ "vision_model.encoder.layers.23.ls2": "model-00002-of-00011.safetensors",
570
+ "vision_model.encoder.layers.23.mlp.fc1.bias": "model-00002-of-00011.safetensors",
571
+ "vision_model.encoder.layers.23.mlp.fc1.weight": "model-00002-of-00011.safetensors",
572
+ "vision_model.encoder.layers.23.mlp.fc2.bias": "model-00002-of-00011.safetensors",
573
+ "vision_model.encoder.layers.23.mlp.fc2.weight": "model-00002-of-00011.safetensors",
574
+ "vision_model.encoder.layers.23.norm1.weight": "model-00002-of-00011.safetensors",
575
+ "vision_model.encoder.layers.23.norm2.weight": "model-00002-of-00011.safetensors",
576
+ "vision_model.encoder.layers.24.attn.k_norm.weight": "model-00002-of-00011.safetensors",
577
+ "vision_model.encoder.layers.24.attn.proj.bias": "model-00002-of-00011.safetensors",
578
+ "vision_model.encoder.layers.24.attn.proj.weight": "model-00002-of-00011.safetensors",
579
+ "vision_model.encoder.layers.24.attn.q_norm.weight": "model-00002-of-00011.safetensors",
580
+ "vision_model.encoder.layers.24.attn.qkv.weight": "model-00002-of-00011.safetensors",
581
+ "vision_model.encoder.layers.24.ls1": "model-00002-of-00011.safetensors",
582
+ "vision_model.encoder.layers.24.ls2": "model-00002-of-00011.safetensors",
583
+ "vision_model.encoder.layers.24.mlp.fc1.bias": "model-00002-of-00011.safetensors",
584
+ "vision_model.encoder.layers.24.mlp.fc1.weight": "model-00002-of-00011.safetensors",
585
+ "vision_model.encoder.layers.24.mlp.fc2.bias": "model-00002-of-00011.safetensors",
586
+ "vision_model.encoder.layers.24.mlp.fc2.weight": "model-00002-of-00011.safetensors",
587
+ "vision_model.encoder.layers.24.norm1.weight": "model-00002-of-00011.safetensors",
588
+ "vision_model.encoder.layers.24.norm2.weight": "model-00002-of-00011.safetensors",
589
+ "vision_model.encoder.layers.25.attn.k_norm.weight": "model-00002-of-00011.safetensors",
590
+ "vision_model.encoder.layers.25.attn.proj.bias": "model-00002-of-00011.safetensors",
591
+ "vision_model.encoder.layers.25.attn.proj.weight": "model-00002-of-00011.safetensors",
592
+ "vision_model.encoder.layers.25.attn.q_norm.weight": "model-00002-of-00011.safetensors",
593
+ "vision_model.encoder.layers.25.attn.qkv.weight": "model-00002-of-00011.safetensors",
594
+ "vision_model.encoder.layers.25.ls1": "model-00002-of-00011.safetensors",
595
+ "vision_model.encoder.layers.25.ls2": "model-00002-of-00011.safetensors",
596
+ "vision_model.encoder.layers.25.mlp.fc1.bias": "model-00002-of-00011.safetensors",
597
+ "vision_model.encoder.layers.25.mlp.fc1.weight": "model-00002-of-00011.safetensors",
598
+ "vision_model.encoder.layers.25.mlp.fc2.bias": "model-00002-of-00011.safetensors",
599
+ "vision_model.encoder.layers.25.mlp.fc2.weight": "model-00002-of-00011.safetensors",
600
+ "vision_model.encoder.layers.25.norm1.weight": "model-00002-of-00011.safetensors",
601
+ "vision_model.encoder.layers.25.norm2.weight": "model-00002-of-00011.safetensors",
602
+ "vision_model.encoder.layers.26.attn.k_norm.weight": "model-00002-of-00011.safetensors",
603
+ "vision_model.encoder.layers.26.attn.proj.bias": "model-00002-of-00011.safetensors",
604
+ "vision_model.encoder.layers.26.attn.proj.weight": "model-00002-of-00011.safetensors",
605
+ "vision_model.encoder.layers.26.attn.q_norm.weight": "model-00002-of-00011.safetensors",
606
+ "vision_model.encoder.layers.26.attn.qkv.weight": "model-00002-of-00011.safetensors",
607
+ "vision_model.encoder.layers.26.ls1": "model-00002-of-00011.safetensors",
608
+ "vision_model.encoder.layers.26.ls2": "model-00002-of-00011.safetensors",
609
+ "vision_model.encoder.layers.26.mlp.fc1.bias": "model-00002-of-00011.safetensors",
610
+ "vision_model.encoder.layers.26.mlp.fc1.weight": "model-00002-of-00011.safetensors",
611
+ "vision_model.encoder.layers.26.mlp.fc2.bias": "model-00002-of-00011.safetensors",
612
+ "vision_model.encoder.layers.26.mlp.fc2.weight": "model-00002-of-00011.safetensors",
613
+ "vision_model.encoder.layers.26.norm1.weight": "model-00002-of-00011.safetensors",
614
+ "vision_model.encoder.layers.26.norm2.weight": "model-00002-of-00011.safetensors",
615
+ "vision_model.encoder.layers.27.attn.k_norm.weight": "model-00002-of-00011.safetensors",
616
+ "vision_model.encoder.layers.27.attn.proj.bias": "model-00002-of-00011.safetensors",
617
+ "vision_model.encoder.layers.27.attn.proj.weight": "model-00002-of-00011.safetensors",
618
+ "vision_model.encoder.layers.27.attn.q_norm.weight": "model-00002-of-00011.safetensors",
619
+ "vision_model.encoder.layers.27.attn.qkv.weight": "model-00002-of-00011.safetensors",
620
+ "vision_model.encoder.layers.27.ls1": "model-00002-of-00011.safetensors",
621
+ "vision_model.encoder.layers.27.ls2": "model-00002-of-00011.safetensors",
622
+ "vision_model.encoder.layers.27.mlp.fc1.bias": "model-00002-of-00011.safetensors",
623
+ "vision_model.encoder.layers.27.mlp.fc1.weight": "model-00002-of-00011.safetensors",
624
+ "vision_model.encoder.layers.27.mlp.fc2.bias": "model-00002-of-00011.safetensors",
625
+ "vision_model.encoder.layers.27.mlp.fc2.weight": "model-00002-of-00011.safetensors",
626
+ "vision_model.encoder.layers.27.norm1.weight": "model-00002-of-00011.safetensors",
627
+ "vision_model.encoder.layers.27.norm2.weight": "model-00002-of-00011.safetensors",
628
+ "vision_model.encoder.layers.28.attn.k_norm.weight": "model-00002-of-00011.safetensors",
629
+ "vision_model.encoder.layers.28.attn.proj.bias": "model-00002-of-00011.safetensors",
630
+ "vision_model.encoder.layers.28.attn.proj.weight": "model-00002-of-00011.safetensors",
631
+ "vision_model.encoder.layers.28.attn.q_norm.weight": "model-00002-of-00011.safetensors",
632
+ "vision_model.encoder.layers.28.attn.qkv.weight": "model-00002-of-00011.safetensors",
633
+ "vision_model.encoder.layers.28.ls1": "model-00002-of-00011.safetensors",
634
+ "vision_model.encoder.layers.28.ls2": "model-00002-of-00011.safetensors",
635
+ "vision_model.encoder.layers.28.mlp.fc1.bias": "model-00002-of-00011.safetensors",
636
+ "vision_model.encoder.layers.28.mlp.fc1.weight": "model-00002-of-00011.safetensors",
637
+ "vision_model.encoder.layers.28.mlp.fc2.bias": "model-00002-of-00011.safetensors",
638
+ "vision_model.encoder.layers.28.mlp.fc2.weight": "model-00002-of-00011.safetensors",
639
+ "vision_model.encoder.layers.28.norm1.weight": "model-00002-of-00011.safetensors",
640
+ "vision_model.encoder.layers.28.norm2.weight": "model-00002-of-00011.safetensors",
641
+ "vision_model.encoder.layers.29.attn.k_norm.weight": "model-00002-of-00011.safetensors",
642
+ "vision_model.encoder.layers.29.attn.proj.bias": "model-00002-of-00011.safetensors",
643
+ "vision_model.encoder.layers.29.attn.proj.weight": "model-00002-of-00011.safetensors",
644
+ "vision_model.encoder.layers.29.attn.q_norm.weight": "model-00002-of-00011.safetensors",
645
+ "vision_model.encoder.layers.29.attn.qkv.weight": "model-00002-of-00011.safetensors",
646
+ "vision_model.encoder.layers.29.ls1": "model-00002-of-00011.safetensors",
647
+ "vision_model.encoder.layers.29.ls2": "model-00002-of-00011.safetensors",
648
+ "vision_model.encoder.layers.29.mlp.fc1.bias": "model-00002-of-00011.safetensors",
649
+ "vision_model.encoder.layers.29.mlp.fc1.weight": "model-00002-of-00011.safetensors",
650
+ "vision_model.encoder.layers.29.mlp.fc2.bias": "model-00002-of-00011.safetensors",
651
+ "vision_model.encoder.layers.29.mlp.fc2.weight": "model-00002-of-00011.safetensors",
652
+ "vision_model.encoder.layers.29.norm1.weight": "model-00002-of-00011.safetensors",
653
+ "vision_model.encoder.layers.29.norm2.weight": "model-00002-of-00011.safetensors",
654
+ "vision_model.encoder.layers.3.attn.k_norm.weight": "model-00001-of-00011.safetensors",
655
+ "vision_model.encoder.layers.3.attn.proj.bias": "model-00001-of-00011.safetensors",
656
+ "vision_model.encoder.layers.3.attn.proj.weight": "model-00001-of-00011.safetensors",
657
+ "vision_model.encoder.layers.3.attn.q_norm.weight": "model-00001-of-00011.safetensors",
658
+ "vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00011.safetensors",
659
+ "vision_model.encoder.layers.3.ls1": "model-00001-of-00011.safetensors",
660
+ "vision_model.encoder.layers.3.ls2": "model-00001-of-00011.safetensors",
661
+ "vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00011.safetensors",
662
+ "vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00011.safetensors",
663
+ "vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00011.safetensors",
664
+ "vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00011.safetensors",
665
+ "vision_model.encoder.layers.3.norm1.weight": "model-00001-of-00011.safetensors",
666
+ "vision_model.encoder.layers.3.norm2.weight": "model-00001-of-00011.safetensors",
667
+ "vision_model.encoder.layers.30.attn.k_norm.weight": "model-00002-of-00011.safetensors",
668
+ "vision_model.encoder.layers.30.attn.proj.bias": "model-00002-of-00011.safetensors",
669
+ "vision_model.encoder.layers.30.attn.proj.weight": "model-00002-of-00011.safetensors",
670
+ "vision_model.encoder.layers.30.attn.q_norm.weight": "model-00002-of-00011.safetensors",
671
+ "vision_model.encoder.layers.30.attn.qkv.weight": "model-00002-of-00011.safetensors",
672
+ "vision_model.encoder.layers.30.ls1": "model-00002-of-00011.safetensors",
673
+ "vision_model.encoder.layers.30.ls2": "model-00002-of-00011.safetensors",
674
+ "vision_model.encoder.layers.30.mlp.fc1.bias": "model-00002-of-00011.safetensors",
675
+ "vision_model.encoder.layers.30.mlp.fc1.weight": "model-00002-of-00011.safetensors",
676
+ "vision_model.encoder.layers.30.mlp.fc2.bias": "model-00002-of-00011.safetensors",
677
+ "vision_model.encoder.layers.30.mlp.fc2.weight": "model-00002-of-00011.safetensors",
678
+ "vision_model.encoder.layers.30.norm1.weight": "model-00002-of-00011.safetensors",
679
+ "vision_model.encoder.layers.30.norm2.weight": "model-00002-of-00011.safetensors",
680
+ "vision_model.encoder.layers.31.attn.k_norm.weight": "model-00002-of-00011.safetensors",
681
+ "vision_model.encoder.layers.31.attn.proj.bias": "model-00002-of-00011.safetensors",
682
+ "vision_model.encoder.layers.31.attn.proj.weight": "model-00002-of-00011.safetensors",
683
+ "vision_model.encoder.layers.31.attn.q_norm.weight": "model-00002-of-00011.safetensors",
684
+ "vision_model.encoder.layers.31.attn.qkv.weight": "model-00002-of-00011.safetensors",
685
+ "vision_model.encoder.layers.31.ls1": "model-00002-of-00011.safetensors",
686
+ "vision_model.encoder.layers.31.ls2": "model-00002-of-00011.safetensors",
687
+ "vision_model.encoder.layers.31.mlp.fc1.bias": "model-00002-of-00011.safetensors",
688
+ "vision_model.encoder.layers.31.mlp.fc1.weight": "model-00002-of-00011.safetensors",
689
+ "vision_model.encoder.layers.31.mlp.fc2.bias": "model-00002-of-00011.safetensors",
690
+ "vision_model.encoder.layers.31.mlp.fc2.weight": "model-00002-of-00011.safetensors",
691
+ "vision_model.encoder.layers.31.norm1.weight": "model-00002-of-00011.safetensors",
692
+ "vision_model.encoder.layers.31.norm2.weight": "model-00002-of-00011.safetensors",
693
+ "vision_model.encoder.layers.32.attn.k_norm.weight": "model-00002-of-00011.safetensors",
694
+ "vision_model.encoder.layers.32.attn.proj.bias": "model-00002-of-00011.safetensors",
695
+ "vision_model.encoder.layers.32.attn.proj.weight": "model-00002-of-00011.safetensors",
696
+ "vision_model.encoder.layers.32.attn.q_norm.weight": "model-00002-of-00011.safetensors",
697
+ "vision_model.encoder.layers.32.attn.qkv.weight": "model-00002-of-00011.safetensors",
698
+ "vision_model.encoder.layers.32.ls1": "model-00002-of-00011.safetensors",
699
+ "vision_model.encoder.layers.32.ls2": "model-00002-of-00011.safetensors",
700
+ "vision_model.encoder.layers.32.mlp.fc1.bias": "model-00002-of-00011.safetensors",
701
+ "vision_model.encoder.layers.32.mlp.fc1.weight": "model-00002-of-00011.safetensors",
702
+ "vision_model.encoder.layers.32.mlp.fc2.bias": "model-00002-of-00011.safetensors",
703
+ "vision_model.encoder.layers.32.mlp.fc2.weight": "model-00002-of-00011.safetensors",
704
+ "vision_model.encoder.layers.32.norm1.weight": "model-00002-of-00011.safetensors",
705
+ "vision_model.encoder.layers.32.norm2.weight": "model-00002-of-00011.safetensors",
706
+ "vision_model.encoder.layers.33.attn.k_norm.weight": "model-00002-of-00011.safetensors",
707
+ "vision_model.encoder.layers.33.attn.proj.bias": "model-00002-of-00011.safetensors",
708
+ "vision_model.encoder.layers.33.attn.proj.weight": "model-00002-of-00011.safetensors",
709
+ "vision_model.encoder.layers.33.attn.q_norm.weight": "model-00002-of-00011.safetensors",
710
+ "vision_model.encoder.layers.33.attn.qkv.weight": "model-00002-of-00011.safetensors",
711
+ "vision_model.encoder.layers.33.ls1": "model-00002-of-00011.safetensors",
712
+ "vision_model.encoder.layers.33.ls2": "model-00002-of-00011.safetensors",
713
+ "vision_model.encoder.layers.33.mlp.fc1.bias": "model-00002-of-00011.safetensors",
714
+ "vision_model.encoder.layers.33.mlp.fc1.weight": "model-00002-of-00011.safetensors",
715
+ "vision_model.encoder.layers.33.mlp.fc2.bias": "model-00002-of-00011.safetensors",
716
+ "vision_model.encoder.layers.33.mlp.fc2.weight": "model-00002-of-00011.safetensors",
717
+ "vision_model.encoder.layers.33.norm1.weight": "model-00002-of-00011.safetensors",
718
+ "vision_model.encoder.layers.33.norm2.weight": "model-00002-of-00011.safetensors",
719
+ "vision_model.encoder.layers.34.attn.k_norm.weight": "model-00002-of-00011.safetensors",
720
+ "vision_model.encoder.layers.34.attn.proj.bias": "model-00002-of-00011.safetensors",
721
+ "vision_model.encoder.layers.34.attn.proj.weight": "model-00002-of-00011.safetensors",
722
+ "vision_model.encoder.layers.34.attn.q_norm.weight": "model-00002-of-00011.safetensors",
723
+ "vision_model.encoder.layers.34.attn.qkv.weight": "model-00002-of-00011.safetensors",
724
+ "vision_model.encoder.layers.34.ls1": "model-00002-of-00011.safetensors",
725
+ "vision_model.encoder.layers.34.ls2": "model-00002-of-00011.safetensors",
726
+ "vision_model.encoder.layers.34.mlp.fc1.bias": "model-00002-of-00011.safetensors",
727
+ "vision_model.encoder.layers.34.mlp.fc1.weight": "model-00002-of-00011.safetensors",
728
+ "vision_model.encoder.layers.34.mlp.fc2.bias": "model-00002-of-00011.safetensors",
729
+ "vision_model.encoder.layers.34.mlp.fc2.weight": "model-00002-of-00011.safetensors",
730
+ "vision_model.encoder.layers.34.norm1.weight": "model-00002-of-00011.safetensors",
731
+ "vision_model.encoder.layers.34.norm2.weight": "model-00002-of-00011.safetensors",
732
+ "vision_model.encoder.layers.35.attn.k_norm.weight": "model-00002-of-00011.safetensors",
733
+ "vision_model.encoder.layers.35.attn.proj.bias": "model-00002-of-00011.safetensors",
734
+ "vision_model.encoder.layers.35.attn.proj.weight": "model-00002-of-00011.safetensors",
735
+ "vision_model.encoder.layers.35.attn.q_norm.weight": "model-00002-of-00011.safetensors",
736
+ "vision_model.encoder.layers.35.attn.qkv.weight": "model-00002-of-00011.safetensors",
737
+ "vision_model.encoder.layers.35.ls1": "model-00002-of-00011.safetensors",
738
+ "vision_model.encoder.layers.35.ls2": "model-00002-of-00011.safetensors",
739
+ "vision_model.encoder.layers.35.mlp.fc1.bias": "model-00002-of-00011.safetensors",
740
+ "vision_model.encoder.layers.35.mlp.fc1.weight": "model-00002-of-00011.safetensors",
741
+ "vision_model.encoder.layers.35.mlp.fc2.bias": "model-00002-of-00011.safetensors",
742
+ "vision_model.encoder.layers.35.mlp.fc2.weight": "model-00002-of-00011.safetensors",
743
+ "vision_model.encoder.layers.35.norm1.weight": "model-00002-of-00011.safetensors",
744
+ "vision_model.encoder.layers.35.norm2.weight": "model-00002-of-00011.safetensors",
745
+ "vision_model.encoder.layers.36.attn.k_norm.weight": "model-00002-of-00011.safetensors",
746
+ "vision_model.encoder.layers.36.attn.proj.bias": "model-00002-of-00011.safetensors",
747
+ "vision_model.encoder.layers.36.attn.proj.weight": "model-00002-of-00011.safetensors",
748
+ "vision_model.encoder.layers.36.attn.q_norm.weight": "model-00002-of-00011.safetensors",
749
+ "vision_model.encoder.layers.36.attn.qkv.weight": "model-00002-of-00011.safetensors",
750
+ "vision_model.encoder.layers.36.ls1": "model-00002-of-00011.safetensors",
751
+ "vision_model.encoder.layers.36.ls2": "model-00002-of-00011.safetensors",
752
+ "vision_model.encoder.layers.36.mlp.fc1.bias": "model-00002-of-00011.safetensors",
753
+ "vision_model.encoder.layers.36.mlp.fc1.weight": "model-00002-of-00011.safetensors",
754
+ "vision_model.encoder.layers.36.mlp.fc2.bias": "model-00002-of-00011.safetensors",
755
+ "vision_model.encoder.layers.36.mlp.fc2.weight": "model-00002-of-00011.safetensors",
756
+ "vision_model.encoder.layers.36.norm1.weight": "model-00002-of-00011.safetensors",
757
+ "vision_model.encoder.layers.36.norm2.weight": "model-00002-of-00011.safetensors",
758
+ "vision_model.encoder.layers.37.attn.k_norm.weight": "model-00002-of-00011.safetensors",
759
+ "vision_model.encoder.layers.37.attn.proj.bias": "model-00002-of-00011.safetensors",
760
+ "vision_model.encoder.layers.37.attn.proj.weight": "model-00002-of-00011.safetensors",
761
+ "vision_model.encoder.layers.37.attn.q_norm.weight": "model-00002-of-00011.safetensors",
762
+ "vision_model.encoder.layers.37.attn.qkv.weight": "model-00002-of-00011.safetensors",
763
+ "vision_model.encoder.layers.37.ls1": "model-00002-of-00011.safetensors",
764
+ "vision_model.encoder.layers.37.ls2": "model-00002-of-00011.safetensors",
765
+ "vision_model.encoder.layers.37.mlp.fc1.bias": "model-00002-of-00011.safetensors",
766
+ "vision_model.encoder.layers.37.mlp.fc1.weight": "model-00002-of-00011.safetensors",
767
+ "vision_model.encoder.layers.37.mlp.fc2.bias": "model-00002-of-00011.safetensors",
768
+ "vision_model.encoder.layers.37.mlp.fc2.weight": "model-00002-of-00011.safetensors",
769
+ "vision_model.encoder.layers.37.norm1.weight": "model-00002-of-00011.safetensors",
770
+ "vision_model.encoder.layers.37.norm2.weight": "model-00002-of-00011.safetensors",
771
+ "vision_model.encoder.layers.38.attn.k_norm.weight": "model-00002-of-00011.safetensors",
772
+ "vision_model.encoder.layers.38.attn.proj.bias": "model-00002-of-00011.safetensors",
773
+ "vision_model.encoder.layers.38.attn.proj.weight": "model-00002-of-00011.safetensors",
774
+ "vision_model.encoder.layers.38.attn.q_norm.weight": "model-00002-of-00011.safetensors",
775
+ "vision_model.encoder.layers.38.attn.qkv.weight": "model-00002-of-00011.safetensors",
776
+ "vision_model.encoder.layers.38.ls1": "model-00002-of-00011.safetensors",
777
+ "vision_model.encoder.layers.38.ls2": "model-00002-of-00011.safetensors",
778
+ "vision_model.encoder.layers.38.mlp.fc1.bias": "model-00002-of-00011.safetensors",
779
+ "vision_model.encoder.layers.38.mlp.fc1.weight": "model-00002-of-00011.safetensors",
780
+ "vision_model.encoder.layers.38.mlp.fc2.bias": "model-00002-of-00011.safetensors",
781
+ "vision_model.encoder.layers.38.mlp.fc2.weight": "model-00002-of-00011.safetensors",
782
+ "vision_model.encoder.layers.38.norm1.weight": "model-00002-of-00011.safetensors",
783
+ "vision_model.encoder.layers.38.norm2.weight": "model-00002-of-00011.safetensors",
784
+ "vision_model.encoder.layers.39.attn.k_norm.weight": "model-00002-of-00011.safetensors",
785
+ "vision_model.encoder.layers.39.attn.proj.bias": "model-00002-of-00011.safetensors",
786
+ "vision_model.encoder.layers.39.attn.proj.weight": "model-00002-of-00011.safetensors",
787
+ "vision_model.encoder.layers.39.attn.q_norm.weight": "model-00002-of-00011.safetensors",
788
+ "vision_model.encoder.layers.39.attn.qkv.weight": "model-00002-of-00011.safetensors",
789
+ "vision_model.encoder.layers.39.ls1": "model-00002-of-00011.safetensors",
790
+ "vision_model.encoder.layers.39.ls2": "model-00002-of-00011.safetensors",
791
+ "vision_model.encoder.layers.39.mlp.fc1.bias": "model-00002-of-00011.safetensors",
792
+ "vision_model.encoder.layers.39.mlp.fc1.weight": "model-00002-of-00011.safetensors",
793
+ "vision_model.encoder.layers.39.mlp.fc2.bias": "model-00002-of-00011.safetensors",
794
+ "vision_model.encoder.layers.39.mlp.fc2.weight": "model-00002-of-00011.safetensors",
795
+ "vision_model.encoder.layers.39.norm1.weight": "model-00002-of-00011.safetensors",
796
+ "vision_model.encoder.layers.39.norm2.weight": "model-00002-of-00011.safetensors",
797
+ "vision_model.encoder.layers.4.attn.k_norm.weight": "model-00001-of-00011.safetensors",
798
+ "vision_model.encoder.layers.4.attn.proj.bias": "model-00001-of-00011.safetensors",
799
+ "vision_model.encoder.layers.4.attn.proj.weight": "model-00001-of-00011.safetensors",
800
+ "vision_model.encoder.layers.4.attn.q_norm.weight": "model-00001-of-00011.safetensors",
801
+ "vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00011.safetensors",
802
+ "vision_model.encoder.layers.4.ls1": "model-00001-of-00011.safetensors",
803
+ "vision_model.encoder.layers.4.ls2": "model-00001-of-00011.safetensors",
804
+ "vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00011.safetensors",
805
+ "vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00011.safetensors",
806
+ "vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00011.safetensors",
807
+ "vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00011.safetensors",
808
+ "vision_model.encoder.layers.4.norm1.weight": "model-00001-of-00011.safetensors",
809
+ "vision_model.encoder.layers.4.norm2.weight": "model-00001-of-00011.safetensors",
810
+ "vision_model.encoder.layers.40.attn.k_norm.weight": "model-00002-of-00011.safetensors",
811
+ "vision_model.encoder.layers.40.attn.proj.bias": "model-00002-of-00011.safetensors",
812
+ "vision_model.encoder.layers.40.attn.proj.weight": "model-00002-of-00011.safetensors",
813
+ "vision_model.encoder.layers.40.attn.q_norm.weight": "model-00002-of-00011.safetensors",
814
+ "vision_model.encoder.layers.40.attn.qkv.weight": "model-00002-of-00011.safetensors",
815
+ "vision_model.encoder.layers.40.ls1": "model-00002-of-00011.safetensors",
816
+ "vision_model.encoder.layers.40.ls2": "model-00002-of-00011.safetensors",
817
+ "vision_model.encoder.layers.40.mlp.fc1.bias": "model-00003-of-00011.safetensors",
818
+ "vision_model.encoder.layers.40.mlp.fc1.weight": "model-00003-of-00011.safetensors",
819
+ "vision_model.encoder.layers.40.mlp.fc2.bias": "model-00003-of-00011.safetensors",
820
+ "vision_model.encoder.layers.40.mlp.fc2.weight": "model-00003-of-00011.safetensors",
821
+ "vision_model.encoder.layers.40.norm1.weight": "model-00003-of-00011.safetensors",
822
+ "vision_model.encoder.layers.40.norm2.weight": "model-00003-of-00011.safetensors",
823
+ "vision_model.encoder.layers.41.attn.k_norm.weight": "model-00003-of-00011.safetensors",
824
+ "vision_model.encoder.layers.41.attn.proj.bias": "model-00003-of-00011.safetensors",
825
+ "vision_model.encoder.layers.41.attn.proj.weight": "model-00003-of-00011.safetensors",
826
+ "vision_model.encoder.layers.41.attn.q_norm.weight": "model-00003-of-00011.safetensors",
827
+ "vision_model.encoder.layers.41.attn.qkv.weight": "model-00003-of-00011.safetensors",
828
+ "vision_model.encoder.layers.41.ls1": "model-00003-of-00011.safetensors",
829
+ "vision_model.encoder.layers.41.ls2": "model-00003-of-00011.safetensors",
830
+ "vision_model.encoder.layers.41.mlp.fc1.bias": "model-00003-of-00011.safetensors",
831
+ "vision_model.encoder.layers.41.mlp.fc1.weight": "model-00003-of-00011.safetensors",
832
+ "vision_model.encoder.layers.41.mlp.fc2.bias": "model-00003-of-00011.safetensors",
833
+ "vision_model.encoder.layers.41.mlp.fc2.weight": "model-00003-of-00011.safetensors",
834
+ "vision_model.encoder.layers.41.norm1.weight": "model-00003-of-00011.safetensors",
835
+ "vision_model.encoder.layers.41.norm2.weight": "model-00003-of-00011.safetensors",
836
+ "vision_model.encoder.layers.42.attn.k_norm.weight": "model-00003-of-00011.safetensors",
837
+ "vision_model.encoder.layers.42.attn.proj.bias": "model-00003-of-00011.safetensors",
838
+ "vision_model.encoder.layers.42.attn.proj.weight": "model-00003-of-00011.safetensors",
839
+ "vision_model.encoder.layers.42.attn.q_norm.weight": "model-00003-of-00011.safetensors",
840
+ "vision_model.encoder.layers.42.attn.qkv.weight": "model-00003-of-00011.safetensors",
841
+ "vision_model.encoder.layers.42.ls1": "model-00003-of-00011.safetensors",
842
+ "vision_model.encoder.layers.42.ls2": "model-00003-of-00011.safetensors",
843
+ "vision_model.encoder.layers.42.mlp.fc1.bias": "model-00003-of-00011.safetensors",
844
+ "vision_model.encoder.layers.42.mlp.fc1.weight": "model-00003-of-00011.safetensors",
845
+ "vision_model.encoder.layers.42.mlp.fc2.bias": "model-00003-of-00011.safetensors",
846
+ "vision_model.encoder.layers.42.mlp.fc2.weight": "model-00003-of-00011.safetensors",
847
+ "vision_model.encoder.layers.42.norm1.weight": "model-00003-of-00011.safetensors",
848
+ "vision_model.encoder.layers.42.norm2.weight": "model-00003-of-00011.safetensors",
849
+ "vision_model.encoder.layers.43.attn.k_norm.weight": "model-00003-of-00011.safetensors",
850
+ "vision_model.encoder.layers.43.attn.proj.bias": "model-00003-of-00011.safetensors",
851
+ "vision_model.encoder.layers.43.attn.proj.weight": "model-00003-of-00011.safetensors",
852
+ "vision_model.encoder.layers.43.attn.q_norm.weight": "model-00003-of-00011.safetensors",
853
+ "vision_model.encoder.layers.43.attn.qkv.weight": "model-00003-of-00011.safetensors",
854
+ "vision_model.encoder.layers.43.ls1": "model-00003-of-00011.safetensors",
855
+ "vision_model.encoder.layers.43.ls2": "model-00003-of-00011.safetensors",
856
+ "vision_model.encoder.layers.43.mlp.fc1.bias": "model-00003-of-00011.safetensors",
857
+ "vision_model.encoder.layers.43.mlp.fc1.weight": "model-00003-of-00011.safetensors",
858
+ "vision_model.encoder.layers.43.mlp.fc2.bias": "model-00003-of-00011.safetensors",
859
+ "vision_model.encoder.layers.43.mlp.fc2.weight": "model-00003-of-00011.safetensors",
860
+ "vision_model.encoder.layers.43.norm1.weight": "model-00003-of-00011.safetensors",
861
+ "vision_model.encoder.layers.43.norm2.weight": "model-00003-of-00011.safetensors",
862
+ "vision_model.encoder.layers.44.attn.k_norm.weight": "model-00003-of-00011.safetensors",
863
+ "vision_model.encoder.layers.44.attn.proj.bias": "model-00003-of-00011.safetensors",
864
+ "vision_model.encoder.layers.44.attn.proj.weight": "model-00003-of-00011.safetensors",
865
+ "vision_model.encoder.layers.44.attn.q_norm.weight": "model-00003-of-00011.safetensors",
866
+ "vision_model.encoder.layers.44.attn.qkv.weight": "model-00003-of-00011.safetensors",
867
+ "vision_model.encoder.layers.44.ls1": "model-00003-of-00011.safetensors",
868
+ "vision_model.encoder.layers.44.ls2": "model-00003-of-00011.safetensors",
869
+ "vision_model.encoder.layers.44.mlp.fc1.bias": "model-00003-of-00011.safetensors",
870
+ "vision_model.encoder.layers.44.mlp.fc1.weight": "model-00003-of-00011.safetensors",
871
+ "vision_model.encoder.layers.44.mlp.fc2.bias": "model-00003-of-00011.safetensors",
872
+ "vision_model.encoder.layers.44.mlp.fc2.weight": "model-00003-of-00011.safetensors",
873
+ "vision_model.encoder.layers.44.norm1.weight": "model-00003-of-00011.safetensors",
874
+ "vision_model.encoder.layers.44.norm2.weight": "model-00003-of-00011.safetensors",
875
+ "vision_model.encoder.layers.5.attn.k_norm.weight": "model-00001-of-00011.safetensors",
876
+ "vision_model.encoder.layers.5.attn.proj.bias": "model-00001-of-00011.safetensors",
877
+ "vision_model.encoder.layers.5.attn.proj.weight": "model-00001-of-00011.safetensors",
878
+ "vision_model.encoder.layers.5.attn.q_norm.weight": "model-00001-of-00011.safetensors",
879
+ "vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00011.safetensors",
880
+ "vision_model.encoder.layers.5.ls1": "model-00001-of-00011.safetensors",
881
+ "vision_model.encoder.layers.5.ls2": "model-00001-of-00011.safetensors",
882
+ "vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00011.safetensors",
883
+ "vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00011.safetensors",
884
+ "vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00011.safetensors",
885
+ "vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00011.safetensors",
886
+ "vision_model.encoder.layers.5.norm1.weight": "model-00001-of-00011.safetensors",
887
+ "vision_model.encoder.layers.5.norm2.weight": "model-00001-of-00011.safetensors",
888
+ "vision_model.encoder.layers.6.attn.k_norm.weight": "model-00001-of-00011.safetensors",
889
+ "vision_model.encoder.layers.6.attn.proj.bias": "model-00001-of-00011.safetensors",
890
+ "vision_model.encoder.layers.6.attn.proj.weight": "model-00001-of-00011.safetensors",
891
+ "vision_model.encoder.layers.6.attn.q_norm.weight": "model-00001-of-00011.safetensors",
892
+ "vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00011.safetensors",
893
+ "vision_model.encoder.layers.6.ls1": "model-00001-of-00011.safetensors",
894
+ "vision_model.encoder.layers.6.ls2": "model-00001-of-00011.safetensors",
895
+ "vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00011.safetensors",
896
+ "vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00011.safetensors",
897
+ "vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00011.safetensors",
898
+ "vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00011.safetensors",
899
+ "vision_model.encoder.layers.6.norm1.weight": "model-00001-of-00011.safetensors",
900
+ "vision_model.encoder.layers.6.norm2.weight": "model-00001-of-00011.safetensors",
901
+ "vision_model.encoder.layers.7.attn.k_norm.weight": "model-00001-of-00011.safetensors",
902
+ "vision_model.encoder.layers.7.attn.proj.bias": "model-00001-of-00011.safetensors",
903
+ "vision_model.encoder.layers.7.attn.proj.weight": "model-00001-of-00011.safetensors",
904
+ "vision_model.encoder.layers.7.attn.q_norm.weight": "model-00001-of-00011.safetensors",
905
+ "vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00011.safetensors",
906
+ "vision_model.encoder.layers.7.ls1": "model-00001-of-00011.safetensors",
907
+ "vision_model.encoder.layers.7.ls2": "model-00001-of-00011.safetensors",
908
+ "vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00011.safetensors",
909
+ "vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00011.safetensors",
910
+ "vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00011.safetensors",
911
+ "vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00011.safetensors",
912
+ "vision_model.encoder.layers.7.norm1.weight": "model-00001-of-00011.safetensors",
913
+ "vision_model.encoder.layers.7.norm2.weight": "model-00001-of-00011.safetensors",
914
+ "vision_model.encoder.layers.8.attn.k_norm.weight": "model-00001-of-00011.safetensors",
915
+ "vision_model.encoder.layers.8.attn.proj.bias": "model-00001-of-00011.safetensors",
916
+ "vision_model.encoder.layers.8.attn.proj.weight": "model-00001-of-00011.safetensors",
917
+ "vision_model.encoder.layers.8.attn.q_norm.weight": "model-00001-of-00011.safetensors",
918
+ "vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00011.safetensors",
919
+ "vision_model.encoder.layers.8.ls1": "model-00001-of-00011.safetensors",
920
+ "vision_model.encoder.layers.8.ls2": "model-00001-of-00011.safetensors",
921
+ "vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00011.safetensors",
922
+ "vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00011.safetensors",
923
+ "vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00011.safetensors",
924
+ "vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00011.safetensors",
925
+ "vision_model.encoder.layers.8.norm1.weight": "model-00001-of-00011.safetensors",
926
+ "vision_model.encoder.layers.8.norm2.weight": "model-00001-of-00011.safetensors",
927
+ "vision_model.encoder.layers.9.attn.k_norm.weight": "model-00001-of-00011.safetensors",
928
+ "vision_model.encoder.layers.9.attn.proj.bias": "model-00001-of-00011.safetensors",
929
+ "vision_model.encoder.layers.9.attn.proj.weight": "model-00001-of-00011.safetensors",
930
+ "vision_model.encoder.layers.9.attn.q_norm.weight": "model-00001-of-00011.safetensors",
931
+ "vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00011.safetensors",
932
+ "vision_model.encoder.layers.9.ls1": "model-00001-of-00011.safetensors",
933
+ "vision_model.encoder.layers.9.ls2": "model-00001-of-00011.safetensors",
934
+ "vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00011.safetensors",
935
+ "vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00011.safetensors",
936
+ "vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00011.safetensors",
937
+ "vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00011.safetensors",
938
+ "vision_model.encoder.layers.9.norm1.weight": "model-00001-of-00011.safetensors",
939
+ "vision_model.encoder.layers.9.norm2.weight": "model-00001-of-00011.safetensors"
940
+ }
941
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<img>",
4
+ "</img>",
5
+ "<IMG_CONTEXT>",
6
+ "<quad>",
7
+ "</quad>",
8
+ "<ref>",
9
+ "</ref>",
10
+ "<box>",
11
+ "</box>"
12
+ ],
13
+ "bos_token": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "pad_token": {
28
+ "content": "</s>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "unk_token": {
35
+ "content": "<unk>",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ }
41
+ }
tokenization_internlm2.py ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Copyright (c) The InternLM team and The HuggingFace Inc. team. All rights reserved.
2
+ #
3
+ # This code is based on transformers/src/transformers/models/llama/tokenization_llama.py
4
+ #
5
+ # Licensed under the Apache License, Version 2.0 (the "License");
6
+ # you may not use this file except in compliance with the License.
7
+ # You may obtain a copy of the License at
8
+ #
9
+ # http://www.apache.org/licenses/LICENSE-2.0
10
+ #
11
+ # Unless required by applicable law or agreed to in writing, software
12
+ # distributed under the License is distributed on an "AS IS" BASIS,
13
+ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14
+ # See the License for the specific language governing permissions and
15
+ # limitations under the License.
16
+
17
+ """Tokenization classes for InternLM."""
18
+ import os
19
+ from shutil import copyfile
20
+ from typing import Any, Dict, List, Optional, Tuple
21
+
22
+ import sentencepiece as spm
23
+ from transformers.tokenization_utils import PreTrainedTokenizer
24
+ from transformers.utils import logging
25
+
26
+ logger = logging.get_logger(__name__)
27
+
28
+ VOCAB_FILES_NAMES = {'vocab_file': './tokenizer.model'}
29
+
30
+ PRETRAINED_VOCAB_FILES_MAP = {}
31
+
32
+
33
+ # Modified from transformers.model.llama.tokenization_llama.LlamaTokenizer
34
+ class InternLM2Tokenizer(PreTrainedTokenizer):
35
+ """
36
+ Construct a InternLM2 tokenizer. Based on byte-level Byte-Pair-Encoding.
37
+
38
+ Args:
39
+ vocab_file (`str`):
40
+ Path to the vocabulary file.
41
+ """
42
+
43
+ vocab_files_names = VOCAB_FILES_NAMES
44
+ pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
45
+ model_input_names = ['input_ids', 'attention_mask']
46
+ _auto_class = 'AutoTokenizer'
47
+
48
+ def __init__(
49
+ self,
50
+ vocab_file,
51
+ unk_token='<unk>',
52
+ bos_token='<s>',
53
+ eos_token='</s>',
54
+ pad_token='</s>',
55
+ sp_model_kwargs: Optional[Dict[str, Any]] = None,
56
+ add_bos_token=True,
57
+ add_eos_token=False,
58
+ decode_with_prefix_space=False,
59
+ clean_up_tokenization_spaces=False,
60
+ **kwargs,
61
+ ):
62
+ self.sp_model_kwargs = {} if sp_model_kwargs is None else sp_model_kwargs
63
+ self.vocab_file = vocab_file
64
+ self.add_bos_token = add_bos_token
65
+ self.add_eos_token = add_eos_token
66
+ self.decode_with_prefix_space = decode_with_prefix_space
67
+ self.sp_model = spm.SentencePieceProcessor(**self.sp_model_kwargs)
68
+ self.sp_model.Load(vocab_file)
69
+ self._no_prefix_space_tokens = None
70
+ super().__init__(
71
+ bos_token=bos_token,
72
+ eos_token=eos_token,
73
+ unk_token=unk_token,
74
+ pad_token=pad_token,
75
+ clean_up_tokenization_spaces=clean_up_tokenization_spaces,
76
+ **kwargs,
77
+ )
78
+
79
+ @property
80
+ def no_prefix_space_tokens(self):
81
+ if self._no_prefix_space_tokens is None:
82
+ vocab = self.convert_ids_to_tokens(list(range(self.vocab_size)))
83
+ self._no_prefix_space_tokens = {i for i, tok in enumerate(vocab) if not tok.startswith('▁')}
84
+ return self._no_prefix_space_tokens
85
+
86
+ @property
87
+ def vocab_size(self):
88
+ """Returns vocab size"""
89
+ return self.sp_model.get_piece_size()
90
+
91
+ @property
92
+ def bos_token_id(self) -> Optional[int]:
93
+ return self.sp_model.bos_id()
94
+
95
+ @property
96
+ def eos_token_id(self) -> Optional[int]:
97
+ return self.sp_model.eos_id()
98
+
99
+ def get_vocab(self):
100
+ """Returns vocab as a dict"""
101
+ vocab = {self.convert_ids_to_tokens(i): i for i in range(self.vocab_size)}
102
+ vocab.update(self.added_tokens_encoder)
103
+ return vocab
104
+
105
+ def _tokenize(self, text):
106
+ """Returns a tokenized string."""
107
+ return self.sp_model.encode(text, out_type=str)
108
+
109
+ def _convert_token_to_id(self, token):
110
+ """Converts a token (str) in an id using the vocab."""
111
+ return self.sp_model.piece_to_id(token)
112
+
113
+ def _convert_id_to_token(self, index):
114
+ """Converts an index (integer) in a token (str) using the vocab."""
115
+ token = self.sp_model.IdToPiece(index)
116
+ return token
117
+
118
+ def _maybe_add_prefix_space(self, tokens, decoded):
119
+ if tokens and tokens[0] not in self.no_prefix_space_tokens:
120
+ return ' ' + decoded
121
+ else:
122
+ return decoded
123
+
124
+ def convert_tokens_to_string(self, tokens):
125
+ """Converts a sequence of tokens (string) in a single string."""
126
+ current_sub_tokens = []
127
+ out_string = ''
128
+ prev_is_special = False
129
+ for token in tokens:
130
+ # make sure that special tokens are not decoded using sentencepiece model
131
+ if token in self.all_special_tokens:
132
+ if not prev_is_special:
133
+ out_string += ' '
134
+ out_string += self.sp_model.decode(current_sub_tokens) + token
135
+ prev_is_special = True
136
+ current_sub_tokens = []
137
+ else:
138
+ current_sub_tokens.append(token)
139
+ prev_is_special = False
140
+ out_string += self.sp_model.decode(current_sub_tokens)
141
+ out_string = self.clean_up_tokenization(out_string)
142
+ out_string = self._maybe_add_prefix_space(tokens=tokens, decoded=out_string)
143
+ return out_string[1:]
144
+
145
+ def save_vocabulary(self, save_directory, filename_prefix: Optional[str] = None) -> Tuple[str]:
146
+ """
147
+ Save the vocabulary and special tokens file to a directory.
148
+
149
+ Args:
150
+ save_directory (`str`):
151
+ The directory in which to save the vocabulary.
152
+
153
+ Returns:
154
+ `Tuple(str)`: Paths to the files saved.
155
+ """
156
+ if not os.path.isdir(save_directory):
157
+ logger.error(f'Vocabulary path ({save_directory}) should be a directory')
158
+ return
159
+ out_vocab_file = os.path.join(
160
+ save_directory, (filename_prefix + '-' if filename_prefix else '') + VOCAB_FILES_NAMES['vocab_file']
161
+ )
162
+
163
+ if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file) and os.path.isfile(self.vocab_file):
164
+ copyfile(self.vocab_file, out_vocab_file)
165
+ elif not os.path.isfile(self.vocab_file):
166
+ with open(out_vocab_file, 'wb') as fi:
167
+ content_spiece_model = self.sp_model.serialized_model_proto()
168
+ fi.write(content_spiece_model)
169
+
170
+ return (out_vocab_file,)
171
+
172
+ def build_inputs_with_special_tokens(self, token_ids_0, token_ids_1=None):
173
+ if self.add_bos_token:
174
+ bos_token_ids = [self.bos_token_id]
175
+ else:
176
+ bos_token_ids = []
177
+
178
+ output = bos_token_ids + token_ids_0
179
+
180
+ if token_ids_1 is not None:
181
+ output = output + token_ids_1
182
+
183
+ if self.add_eos_token:
184
+ output = output + [self.eos_token_id]
185
+
186
+ return output
187
+
188
+ def get_special_tokens_mask(
189
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
190
+ ) -> List[int]:
191
+ """
192
+ Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
193
+ special tokens using the tokenizer `prepare_for_model` method.
194
+
195
+ Args:
196
+ token_ids_0 (`List[int]`):
197
+ List of IDs.
198
+ token_ids_1 (`List[int]`, *optional*):
199
+ Optional second list of IDs for sequence pairs.
200
+ already_has_special_tokens (`bool`, *optional*, defaults to `False`):
201
+ Whether or not the token list is already formatted with special tokens for the model.
202
+
203
+ Returns:
204
+ `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
205
+ """
206
+ if already_has_special_tokens:
207
+ return super().get_special_tokens_mask(
208
+ token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
209
+ )
210
+
211
+ if token_ids_1 is None:
212
+ return [1] + ([0] * len(token_ids_0)) + [1]
213
+ return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]
214
+
215
+ def create_token_type_ids_from_sequences(
216
+ self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
217
+ ) -> List[int]:
218
+ """
219
+ Create a mask from the two sequences passed to be used in a sequence-pair classification task. T5 does not make
220
+ use of token type ids, therefore a list of zeros is returned.
221
+
222
+ Args:
223
+ token_ids_0 (`List[int]`):
224
+ List of IDs.
225
+ token_ids_1 (`List[int]`, *optional*):
226
+ Optional second list of IDs for sequence pairs.
227
+
228
+ Returns:
229
+ `List[int]`: List of zeros.
230
+ """
231
+ eos = [self.eos_token_id]
232
+
233
+ if token_ids_1 is None:
234
+ return len(token_ids_0 + eos) * [0]
235
+ return len(token_ids_0 + eos + token_ids_1 + eos) * [0]
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
3
+ size 1477754
tokenizer_config.json ADDED
@@ -0,0 +1,173 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "92538": {
28
+ "content": "<|plugin|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "92539": {
36
+ "content": "<|interpreter|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "92540": {
44
+ "content": "<|action_end|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "92541": {
52
+ "content": "<|action_start|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "92542": {
60
+ "content": "<|im_end|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "92543": {
68
+ "content": "<|im_start|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "92544": {
76
+ "content": "<img>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "92545": {
84
+ "content": "</img>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "92546": {
92
+ "content": "<IMG_CONTEXT>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "92547": {
100
+ "content": "<quad>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "92548": {
108
+ "content": "</quad>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "92549": {
116
+ "content": "<ref>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "92550": {
124
+ "content": "</ref>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "92551": {
132
+ "content": "<box>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "92552": {
140
+ "content": "</box>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ }
147
+ },
148
+ "additional_special_tokens": [
149
+ "<img>",
150
+ "</img>",
151
+ "<IMG_CONTEXT>",
152
+ "<quad>",
153
+ "</quad>",
154
+ "<ref>",
155
+ "</ref>",
156
+ "<box>",
157
+ "</box>"
158
+ ],
159
+ "auto_map": {
160
+ "AutoTokenizer": [
161
+ "tokenization_internlm2.InternLM2Tokenizer",
162
+ null
163
+ ]
164
+ },
165
+ "bos_token": "<s>",
166
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
167
+ "clean_up_tokenization_spaces": false,
168
+ "eos_token": "</s>",
169
+ "model_max_length": 40000,
170
+ "pad_token": "</s>",
171
+ "tokenizer_class": "InternLM2Tokenizer",
172
+ "unk_token": "<unk>"
173
+ }