Hugging Face's logo

craigwu
/
GUI_Reflection_8b_SFT

Safetensors
internvl_chat
Model card Files Community
1
craigwu commited on
Commit
720d623
·
verified ·
1 Parent(s): 9014cb8

Upload folder using huggingface_hub

Browse files
Files changed (16) hide show
  1. all_results.json +8 -0
  2. config.json +193 -0
  3. generation_config.json +4 -0
  4. model-00001-of-00004.safetensors +3 -0
  5. model-00002-of-00004.safetensors +3 -0
  6. model-00003-of-00004.safetensors +3 -0
  7. model-00004-of-00004.safetensors +3 -0
  8. model.safetensors.index.json +580 -0
  9. special_tokens_map.json +47 -0
  10. tokenization_internlm2.py +235 -0
  11. tokenization_internlm2_fast.py +211 -0
  12. tokenizer.json +0 -0
  13. tokenizer_config.json +183 -0
  14. train_results.json +8 -0
  15. trainer_state.json +0 -0
  16. training_args.bin +3 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.2210330774939678,
4
+ "train_runtime": 11823.142,
5
+ "train_samples": 100012,
6
+ "train_samples_per_second": 8.459,
7
+ "train_steps_per_second": 0.132
8
+ }
config.json ADDED
@@ -0,0 +1,193 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "/mnt/afs/wupenghao/workspace/InternVL-dev2/output/vit0.3b_internlm7b_guimid_stage5_aug_temporal4_memory_cot_Refall_ACfilter_verify_prev_patch12_d250508/",
4
+ "architectures": [
5
+ "InternVLChatModel"
6
+ ],
7
+ "downsample_ratio": 0.5,
8
+ "dynamic_image_size": true,
9
+ "force_image_size": 448,
10
+ "llm_config": {
11
+ "_name_or_path": "/mnt/afs/user/tianhao2/workspace/internvl/internlm2/internlm2_5-7b-chat",
12
+ "add_cross_attention": false,
13
+ "architectures": [
14
+ "InternLM2ForCausalLM"
15
+ ],
16
+ "attn_implementation": "flash_attention_2",
17
+ "auto_map": {
18
+ "AutoConfig": "configuration_internlm2.InternLM2Config",
19
+ "AutoModel": "modeling_internlm2.InternLM2ForCausalLM",
20
+ "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM"
21
+ },
22
+ "bad_words_ids": null,
23
+ "begin_suppress_tokens": null,
24
+ "bias": false,
25
+ "bos_token_id": 1,
26
+ "chunk_size_feed_forward": 0,
27
+ "cross_attention_hidden_size": null,
28
+ "decoder_start_token_id": null,
29
+ "diversity_penalty": 0.0,
30
+ "do_sample": false,
31
+ "early_stopping": false,
32
+ "encoder_no_repeat_ngram_size": 0,
33
+ "eos_token_id": 2,
34
+ "exponential_decay_length_penalty": null,
35
+ "finetuning_task": null,
36
+ "forced_bos_token_id": null,
37
+ "forced_eos_token_id": null,
38
+ "hidden_act": "silu",
39
+ "hidden_size": 4096,
40
+ "id2label": {
41
+ "0": "LABEL_0",
42
+ "1": "LABEL_1"
43
+ },
44
+ "initializer_range": 0.02,
45
+ "intermediate_size": 14336,
46
+ "is_decoder": false,
47
+ "is_encoder_decoder": false,
48
+ "label2id": {
49
+ "LABEL_0": 0,
50
+ "LABEL_1": 1
51
+ },
52
+ "length_penalty": 1.0,
53
+ "max_length": 20,
54
+ "max_position_embeddings": 32768,
55
+ "min_length": 0,
56
+ "model_type": "internlm2",
57
+ "no_repeat_ngram_size": 0,
58
+ "num_attention_heads": 32,
59
+ "num_beam_groups": 1,
60
+ "num_beams": 1,
61
+ "num_hidden_layers": 32,
62
+ "num_key_value_heads": 8,
63
+ "num_return_sequences": 1,
64
+ "output_attentions": false,
65
+ "output_hidden_states": false,
66
+ "output_scores": false,
67
+ "pad_token_id": 2,
68
+ "prefix": null,
69
+ "pretraining_tp": 1,
70
+ "problem_type": null,
71
+ "pruned_heads": {},
72
+ "remove_invalid_values": false,
73
+ "repetition_penalty": 1.0,
74
+ "return_dict": true,
75
+ "return_dict_in_generate": false,
76
+ "rms_norm_eps": 1e-05,
77
+ "rope_scaling": null,
78
+ "rope_theta": 1000000,
79
+ "sep_token_id": null,
80
+ "suppress_tokens": null,
81
+ "task_specific_params": null,
82
+ "temperature": 1.0,
83
+ "tf_legacy_loss": false,
84
+ "tie_encoder_decoder": false,
85
+ "tie_word_embeddings": false,
86
+ "tokenizer_class": null,
87
+ "top_k": 50,
88
+ "top_p": 1.0,
89
+ "torch_dtype": "bfloat16",
90
+ "torchscript": false,
91
+ "transformers_version": "4.37.2",
92
+ "typical_p": 1.0,
93
+ "use_bfloat16": false,
94
+ "use_cache": false,
95
+ "vocab_size": 92544
96
+ },
97
+ "max_dynamic_patch": 12,
98
+ "min_dynamic_patch": 1,
99
+ "model_type": "internvl_chat",
100
+ "pad2square": false,
101
+ "ps_version": "v2",
102
+ "select_layer": -1,
103
+ "template": "internlm2-chat-v3",
104
+ "torch_dtype": "bfloat16",
105
+ "transformers_version": null,
106
+ "use_backbone_lora": 0,
107
+ "use_llm_lora": 0,
108
+ "use_thumbnail": true,
109
+ "vision_config": {
110
+ "_name_or_path": "",
111
+ "add_cross_attention": false,
112
+ "architectures": [
113
+ "InternVisionModel"
114
+ ],
115
+ "attention_dropout": 0.0,
116
+ "bad_words_ids": null,
117
+ "begin_suppress_tokens": null,
118
+ "bos_token_id": null,
119
+ "chunk_size_feed_forward": 0,
120
+ "cross_attention_hidden_size": null,
121
+ "decoder_start_token_id": null,
122
+ "diversity_penalty": 0.0,
123
+ "do_sample": false,
124
+ "drop_path_rate": 0.1,
125
+ "dropout": 0.0,
126
+ "early_stopping": false,
127
+ "encoder_no_repeat_ngram_size": 0,
128
+ "eos_token_id": null,
129
+ "exponential_decay_length_penalty": null,
130
+ "finetuning_task": null,
131
+ "forced_bos_token_id": null,
132
+ "forced_eos_token_id": null,
133
+ "hidden_act": "gelu",
134
+ "hidden_size": 1024,
135
+ "id2label": {
136
+ "0": "LABEL_0",
137
+ "1": "LABEL_1"
138
+ },
139
+ "image_size": 448,
140
+ "initializer_factor": 1.0,
141
+ "initializer_range": 0.02,
142
+ "intermediate_size": 4096,
143
+ "is_decoder": false,
144
+ "is_encoder_decoder": false,
145
+ "label2id": {
146
+ "LABEL_0": 0,
147
+ "LABEL_1": 1
148
+ },
149
+ "layer_norm_eps": 1e-06,
150
+ "length_penalty": 1.0,
151
+ "max_length": 20,
152
+ "min_length": 0,
153
+ "model_type": "intern_vit_6b",
154
+ "no_repeat_ngram_size": 0,
155
+ "norm_type": "layer_norm",
156
+ "num_attention_heads": 16,
157
+ "num_beam_groups": 1,
158
+ "num_beams": 1,
159
+ "num_channels": 3,
160
+ "num_hidden_layers": 24,
161
+ "num_return_sequences": 1,
162
+ "output_attentions": false,
163
+ "output_hidden_states": false,
164
+ "output_scores": false,
165
+ "pad_token_id": null,
166
+ "patch_size": 14,
167
+ "prefix": null,
168
+ "problem_type": null,
169
+ "pruned_heads": {},
170
+ "qk_normalization": false,
171
+ "qkv_bias": true,
172
+ "remove_invalid_values": false,
173
+ "repetition_penalty": 1.0,
174
+ "return_dict": true,
175
+ "return_dict_in_generate": false,
176
+ "sep_token_id": null,
177
+ "suppress_tokens": null,
178
+ "task_specific_params": null,
179
+ "temperature": 1.0,
180
+ "tf_legacy_loss": false,
181
+ "tie_encoder_decoder": false,
182
+ "tie_word_embeddings": true,
183
+ "tokenizer_class": null,
184
+ "top_k": 50,
185
+ "top_p": 1.0,
186
+ "torch_dtype": "bfloat16",
187
+ "torchscript": false,
188
+ "transformers_version": "4.37.2",
189
+ "typical_p": 1.0,
190
+ "use_bfloat16": false,
191
+ "use_flash_attn": true
192
+ }
193
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.37.2"
4
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d7aae06755d487d313be31c352c0fca247d44ee04ff529d227e20f8166e95de
3
+ size 4939870608
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06bf2d5b9abbeaba428ce4ff6ff6eb869c1717adde281f94fff79c4474ef6490
3
+ size 4915914584
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8fa23d3a55726a56343c375b1cae3b5b1741bcbde67aaecd1347857ffbe187f
3
+ size 4915914592
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19486e11c0247bba75eb47591ffa68865884ce08400ab366ed27a0d6b23cc7ee
3
+ size 1378953192
model.safetensors.index.json ADDED
@@ -0,0 +1,580 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16150583296
4
+ },
5
+ "weight_map": {
6
+ "language_model.model.layers.0.attention.wo.weight": "model-00001-of-00004.safetensors",
7
+ "language_model.model.layers.0.attention.wqkv.weight": "model-00001-of-00004.safetensors",
8
+ "language_model.model.layers.0.attention_norm.weight": "model-00001-of-00004.safetensors",
9
+ "language_model.model.layers.0.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
10
+ "language_model.model.layers.0.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
11
+ "language_model.model.layers.0.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
12
+ "language_model.model.layers.0.ffn_norm.weight": "model-00001-of-00004.safetensors",
13
+ "language_model.model.layers.1.attention.wo.weight": "model-00001-of-00004.safetensors",
14
+ "language_model.model.layers.1.attention.wqkv.weight": "model-00001-of-00004.safetensors",
15
+ "language_model.model.layers.1.attention_norm.weight": "model-00001-of-00004.safetensors",
16
+ "language_model.model.layers.1.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
17
+ "language_model.model.layers.1.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
18
+ "language_model.model.layers.1.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
19
+ "language_model.model.layers.1.ffn_norm.weight": "model-00001-of-00004.safetensors",
20
+ "language_model.model.layers.10.attention.wo.weight": "model-00002-of-00004.safetensors",
21
+ "language_model.model.layers.10.attention.wqkv.weight": "model-00002-of-00004.safetensors",
22
+ "language_model.model.layers.10.attention_norm.weight": "model-00002-of-00004.safetensors",
23
+ "language_model.model.layers.10.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
24
+ "language_model.model.layers.10.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
25
+ "language_model.model.layers.10.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
26
+ "language_model.model.layers.10.ffn_norm.weight": "model-00002-of-00004.safetensors",
27
+ "language_model.model.layers.11.attention.wo.weight": "model-00002-of-00004.safetensors",
28
+ "language_model.model.layers.11.attention.wqkv.weight": "model-00002-of-00004.safetensors",
29
+ "language_model.model.layers.11.attention_norm.weight": "model-00002-of-00004.safetensors",
30
+ "language_model.model.layers.11.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
31
+ "language_model.model.layers.11.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
32
+ "language_model.model.layers.11.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
33
+ "language_model.model.layers.11.ffn_norm.weight": "model-00002-of-00004.safetensors",
34
+ "language_model.model.layers.12.attention.wo.weight": "model-00002-of-00004.safetensors",
35
+ "language_model.model.layers.12.attention.wqkv.weight": "model-00002-of-00004.safetensors",
36
+ "language_model.model.layers.12.attention_norm.weight": "model-00002-of-00004.safetensors",
37
+ "language_model.model.layers.12.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
38
+ "language_model.model.layers.12.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
39
+ "language_model.model.layers.12.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
40
+ "language_model.model.layers.12.ffn_norm.weight": "model-00002-of-00004.safetensors",
41
+ "language_model.model.layers.13.attention.wo.weight": "model-00002-of-00004.safetensors",
42
+ "language_model.model.layers.13.attention.wqkv.weight": "model-00002-of-00004.safetensors",
43
+ "language_model.model.layers.13.attention_norm.weight": "model-00002-of-00004.safetensors",
44
+ "language_model.model.layers.13.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
45
+ "language_model.model.layers.13.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
46
+ "language_model.model.layers.13.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
47
+ "language_model.model.layers.13.ffn_norm.weight": "model-00002-of-00004.safetensors",
48
+ "language_model.model.layers.14.attention.wo.weight": "model-00002-of-00004.safetensors",
49
+ "language_model.model.layers.14.attention.wqkv.weight": "model-00002-of-00004.safetensors",
50
+ "language_model.model.layers.14.attention_norm.weight": "model-00002-of-00004.safetensors",
51
+ "language_model.model.layers.14.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
52
+ "language_model.model.layers.14.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
53
+ "language_model.model.layers.14.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
54
+ "language_model.model.layers.14.ffn_norm.weight": "model-00002-of-00004.safetensors",
55
+ "language_model.model.layers.15.attention.wo.weight": "model-00002-of-00004.safetensors",
56
+ "language_model.model.layers.15.attention.wqkv.weight": "model-00002-of-00004.safetensors",
57
+ "language_model.model.layers.15.attention_norm.weight": "model-00002-of-00004.safetensors",
58
+ "language_model.model.layers.15.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
59
+ "language_model.model.layers.15.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
60
+ "language_model.model.layers.15.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
61
+ "language_model.model.layers.15.ffn_norm.weight": "model-00002-of-00004.safetensors",
62
+ "language_model.model.layers.16.attention.wo.weight": "model-00002-of-00004.safetensors",
63
+ "language_model.model.layers.16.attention.wqkv.weight": "model-00002-of-00004.safetensors",
64
+ "language_model.model.layers.16.attention_norm.weight": "model-00002-of-00004.safetensors",
65
+ "language_model.model.layers.16.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
66
+ "language_model.model.layers.16.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
67
+ "language_model.model.layers.16.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
68
+ "language_model.model.layers.16.ffn_norm.weight": "model-00002-of-00004.safetensors",
69
+ "language_model.model.layers.17.attention.wo.weight": "model-00002-of-00004.safetensors",
70
+ "language_model.model.layers.17.attention.wqkv.weight": "model-00002-of-00004.safetensors",
71
+ "language_model.model.layers.17.attention_norm.weight": "model-00002-of-00004.safetensors",
72
+ "language_model.model.layers.17.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
73
+ "language_model.model.layers.17.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
74
+ "language_model.model.layers.17.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
75
+ "language_model.model.layers.17.ffn_norm.weight": "model-00002-of-00004.safetensors",
76
+ "language_model.model.layers.18.attention.wo.weight": "model-00002-of-00004.safetensors",
77
+ "language_model.model.layers.18.attention.wqkv.weight": "model-00002-of-00004.safetensors",
78
+ "language_model.model.layers.18.attention_norm.weight": "model-00002-of-00004.safetensors",
79
+ "language_model.model.layers.18.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
80
+ "language_model.model.layers.18.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
81
+ "language_model.model.layers.18.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
82
+ "language_model.model.layers.18.ffn_norm.weight": "model-00002-of-00004.safetensors",
83
+ "language_model.model.layers.19.attention.wo.weight": "model-00002-of-00004.safetensors",
84
+ "language_model.model.layers.19.attention.wqkv.weight": "model-00002-of-00004.safetensors",
85
+ "language_model.model.layers.19.attention_norm.weight": "model-00003-of-00004.safetensors",
86
+ "language_model.model.layers.19.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
87
+ "language_model.model.layers.19.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
88
+ "language_model.model.layers.19.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
89
+ "language_model.model.layers.19.ffn_norm.weight": "model-00003-of-00004.safetensors",
90
+ "language_model.model.layers.2.attention.wo.weight": "model-00001-of-00004.safetensors",
91
+ "language_model.model.layers.2.attention.wqkv.weight": "model-00001-of-00004.safetensors",
92
+ "language_model.model.layers.2.attention_norm.weight": "model-00001-of-00004.safetensors",
93
+ "language_model.model.layers.2.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
94
+ "language_model.model.layers.2.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
95
+ "language_model.model.layers.2.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
96
+ "language_model.model.layers.2.ffn_norm.weight": "model-00001-of-00004.safetensors",
97
+ "language_model.model.layers.20.attention.wo.weight": "model-00003-of-00004.safetensors",
98
+ "language_model.model.layers.20.attention.wqkv.weight": "model-00003-of-00004.safetensors",
99
+ "language_model.model.layers.20.attention_norm.weight": "model-00003-of-00004.safetensors",
100
+ "language_model.model.layers.20.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
101
+ "language_model.model.layers.20.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
102
+ "language_model.model.layers.20.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
103
+ "language_model.model.layers.20.ffn_norm.weight": "model-00003-of-00004.safetensors",
104
+ "language_model.model.layers.21.attention.wo.weight": "model-00003-of-00004.safetensors",
105
+ "language_model.model.layers.21.attention.wqkv.weight": "model-00003-of-00004.safetensors",
106
+ "language_model.model.layers.21.attention_norm.weight": "model-00003-of-00004.safetensors",
107
+ "language_model.model.layers.21.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
108
+ "language_model.model.layers.21.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
109
+ "language_model.model.layers.21.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
110
+ "language_model.model.layers.21.ffn_norm.weight": "model-00003-of-00004.safetensors",
111
+ "language_model.model.layers.22.attention.wo.weight": "model-00003-of-00004.safetensors",
112
+ "language_model.model.layers.22.attention.wqkv.weight": "model-00003-of-00004.safetensors",
113
+ "language_model.model.layers.22.attention_norm.weight": "model-00003-of-00004.safetensors",
114
+ "language_model.model.layers.22.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
115
+ "language_model.model.layers.22.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
116
+ "language_model.model.layers.22.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
117
+ "language_model.model.layers.22.ffn_norm.weight": "model-00003-of-00004.safetensors",
118
+ "language_model.model.layers.23.attention.wo.weight": "model-00003-of-00004.safetensors",
119
+ "language_model.model.layers.23.attention.wqkv.weight": "model-00003-of-00004.safetensors",
120
+ "language_model.model.layers.23.attention_norm.weight": "model-00003-of-00004.safetensors",
121
+ "language_model.model.layers.23.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
122
+ "language_model.model.layers.23.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
123
+ "language_model.model.layers.23.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
124
+ "language_model.model.layers.23.ffn_norm.weight": "model-00003-of-00004.safetensors",
125
+ "language_model.model.layers.24.attention.wo.weight": "model-00003-of-00004.safetensors",
126
+ "language_model.model.layers.24.attention.wqkv.weight": "model-00003-of-00004.safetensors",
127
+ "language_model.model.layers.24.attention_norm.weight": "model-00003-of-00004.safetensors",
128
+ "language_model.model.layers.24.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
129
+ "language_model.model.layers.24.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
130
+ "language_model.model.layers.24.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
131
+ "language_model.model.layers.24.ffn_norm.weight": "model-00003-of-00004.safetensors",
132
+ "language_model.model.layers.25.attention.wo.weight": "model-00003-of-00004.safetensors",
133
+ "language_model.model.layers.25.attention.wqkv.weight": "model-00003-of-00004.safetensors",
134
+ "language_model.model.layers.25.attention_norm.weight": "model-00003-of-00004.safetensors",
135
+ "language_model.model.layers.25.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
136
+ "language_model.model.layers.25.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
137
+ "language_model.model.layers.25.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
138
+ "language_model.model.layers.25.ffn_norm.weight": "model-00003-of-00004.safetensors",
139
+ "language_model.model.layers.26.attention.wo.weight": "model-00003-of-00004.safetensors",
140
+ "language_model.model.layers.26.attention.wqkv.weight": "model-00003-of-00004.safetensors",
141
+ "language_model.model.layers.26.attention_norm.weight": "model-00003-of-00004.safetensors",
142
+ "language_model.model.layers.26.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
143
+ "language_model.model.layers.26.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
144
+ "language_model.model.layers.26.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
145
+ "language_model.model.layers.26.ffn_norm.weight": "model-00003-of-00004.safetensors",
146
+ "language_model.model.layers.27.attention.wo.weight": "model-00003-of-00004.safetensors",
147
+ "language_model.model.layers.27.attention.wqkv.weight": "model-00003-of-00004.safetensors",
148
+ "language_model.model.layers.27.attention_norm.weight": "model-00003-of-00004.safetensors",
149
+ "language_model.model.layers.27.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
150
+ "language_model.model.layers.27.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
151
+ "language_model.model.layers.27.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
152
+ "language_model.model.layers.27.ffn_norm.weight": "model-00003-of-00004.safetensors",
153
+ "language_model.model.layers.28.attention.wo.weight": "model-00003-of-00004.safetensors",
154
+ "language_model.model.layers.28.attention.wqkv.weight": "model-00003-of-00004.safetensors",
155
+ "language_model.model.layers.28.attention_norm.weight": "model-00003-of-00004.safetensors",
156
+ "language_model.model.layers.28.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
157
+ "language_model.model.layers.28.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
158
+ "language_model.model.layers.28.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
159
+ "language_model.model.layers.28.ffn_norm.weight": "model-00003-of-00004.safetensors",
160
+ "language_model.model.layers.29.attention.wo.weight": "model-00003-of-00004.safetensors",
161
+ "language_model.model.layers.29.attention.wqkv.weight": "model-00003-of-00004.safetensors",
162
+ "language_model.model.layers.29.attention_norm.weight": "model-00003-of-00004.safetensors",
163
+ "language_model.model.layers.29.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
164
+ "language_model.model.layers.29.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
165
+ "language_model.model.layers.29.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
166
+ "language_model.model.layers.29.ffn_norm.weight": "model-00003-of-00004.safetensors",
167
+ "language_model.model.layers.3.attention.wo.weight": "model-00001-of-00004.safetensors",
168
+ "language_model.model.layers.3.attention.wqkv.weight": "model-00001-of-00004.safetensors",
169
+ "language_model.model.layers.3.attention_norm.weight": "model-00001-of-00004.safetensors",
170
+ "language_model.model.layers.3.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
171
+ "language_model.model.layers.3.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
172
+ "language_model.model.layers.3.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
173
+ "language_model.model.layers.3.ffn_norm.weight": "model-00001-of-00004.safetensors",
174
+ "language_model.model.layers.30.attention.wo.weight": "model-00003-of-00004.safetensors",
175
+ "language_model.model.layers.30.attention.wqkv.weight": "model-00003-of-00004.safetensors",
176
+ "language_model.model.layers.30.attention_norm.weight": "model-00004-of-00004.safetensors",
177
+ "language_model.model.layers.30.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
178
+ "language_model.model.layers.30.feed_forward.w2.weight": "model-00004-of-00004.safetensors",
179
+ "language_model.model.layers.30.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
180
+ "language_model.model.layers.30.ffn_norm.weight": "model-00004-of-00004.safetensors",
181
+ "language_model.model.layers.31.attention.wo.weight": "model-00004-of-00004.safetensors",
182
+ "language_model.model.layers.31.attention.wqkv.weight": "model-00004-of-00004.safetensors",
183
+ "language_model.model.layers.31.attention_norm.weight": "model-00004-of-00004.safetensors",
184
+ "language_model.model.layers.31.feed_forward.w1.weight": "model-00004-of-00004.safetensors",
185
+ "language_model.model.layers.31.feed_forward.w2.weight": "model-00004-of-00004.safetensors",
186
+ "language_model.model.layers.31.feed_forward.w3.weight": "model-00004-of-00004.safetensors",
187
+ "language_model.model.layers.31.ffn_norm.weight": "model-00004-of-00004.safetensors",
188
+ "language_model.model.layers.4.attention.wo.weight": "model-00001-of-00004.safetensors",
189
+ "language_model.model.layers.4.attention.wqkv.weight": "model-00001-of-00004.safetensors",
190
+ "language_model.model.layers.4.attention_norm.weight": "model-00001-of-00004.safetensors",
191
+ "language_model.model.layers.4.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
192
+ "language_model.model.layers.4.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
193
+ "language_model.model.layers.4.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
194
+ "language_model.model.layers.4.ffn_norm.weight": "model-00001-of-00004.safetensors",
195
+ "language_model.model.layers.5.attention.wo.weight": "model-00001-of-00004.safetensors",
196
+ "language_model.model.layers.5.attention.wqkv.weight": "model-00001-of-00004.safetensors",
197
+ "language_model.model.layers.5.attention_norm.weight": "model-00001-of-00004.safetensors",
198
+ "language_model.model.layers.5.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
199
+ "language_model.model.layers.5.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
200
+ "language_model.model.layers.5.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
201
+ "language_model.model.layers.5.ffn_norm.weight": "model-00001-of-00004.safetensors",
202
+ "language_model.model.layers.6.attention.wo.weight": "model-00001-of-00004.safetensors",
203
+ "language_model.model.layers.6.attention.wqkv.weight": "model-00001-of-00004.safetensors",
204
+ "language_model.model.layers.6.attention_norm.weight": "model-00001-of-00004.safetensors",
205
+ "language_model.model.layers.6.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
206
+ "language_model.model.layers.6.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
207
+ "language_model.model.layers.6.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
208
+ "language_model.model.layers.6.ffn_norm.weight": "model-00001-of-00004.safetensors",
209
+ "language_model.model.layers.7.attention.wo.weight": "model-00001-of-00004.safetensors",
210
+ "language_model.model.layers.7.attention.wqkv.weight": "model-00001-of-00004.safetensors",
211
+ "language_model.model.layers.7.attention_norm.weight": "model-00001-of-00004.safetensors",
212
+ "language_model.model.layers.7.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
213
+ "language_model.model.layers.7.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
214
+ "language_model.model.layers.7.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
215
+ "language_model.model.layers.7.ffn_norm.weight": "model-00001-of-00004.safetensors",
216
+ "language_model.model.layers.8.attention.wo.weight": "model-00001-of-00004.safetensors",
217
+ "language_model.model.layers.8.attention.wqkv.weight": "model-00001-of-00004.safetensors",
218
+ "language_model.model.layers.8.attention_norm.weight": "model-00002-of-00004.safetensors",
219
+ "language_model.model.layers.8.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
220
+ "language_model.model.layers.8.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
221
+ "language_model.model.layers.8.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
222
+ "language_model.model.layers.8.ffn_norm.weight": "model-00002-of-00004.safetensors",
223
+ "language_model.model.layers.9.attention.wo.weight": "model-00002-of-00004.safetensors",
224
+ "language_model.model.layers.9.attention.wqkv.weight": "model-00002-of-00004.safetensors",
225
+ "language_model.model.layers.9.attention_norm.weight": "model-00002-of-00004.safetensors",
226
+ "language_model.model.layers.9.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
227
+ "language_model.model.layers.9.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
228
+ "language_model.model.layers.9.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
229
+ "language_model.model.layers.9.ffn_norm.weight": "model-00002-of-00004.safetensors",
230
+ "language_model.model.norm.weight": "model-00004-of-00004.safetensors",
231
+ "language_model.model.tok_embeddings.weight": "model-00001-of-00004.safetensors",
232
+ "language_model.output.weight": "model-00004-of-00004.safetensors",
233
+ "mlp1.0.bias": "model-00004-of-00004.safetensors",
234
+ "mlp1.0.weight": "model-00004-of-00004.safetensors",
235
+ "mlp1.1.bias": "model-00004-of-00004.safetensors",
236
+ "mlp1.1.weight": "model-00004-of-00004.safetensors",
237
+ "mlp1.3.bias": "model-00004-of-00004.safetensors",
238
+ "mlp1.3.weight": "model-00004-of-00004.safetensors",
239
+ "vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
240
+ "vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
241
+ "vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
242
+ "vision_model.embeddings.position_embedding": "model-00001-of-00004.safetensors",
243
+ "vision_model.encoder.layers.0.attn.proj.bias": "model-00001-of-00004.safetensors",
244
+ "vision_model.encoder.layers.0.attn.proj.weight": "model-00001-of-00004.safetensors",
245
+ "vision_model.encoder.layers.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
246
+ "vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
247
+ "vision_model.encoder.layers.0.ls1": "model-00001-of-00004.safetensors",
248
+ "vision_model.encoder.layers.0.ls2": "model-00001-of-00004.safetensors",
249
+ "vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
250
+ "vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
251
+ "vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
252
+ "vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
253
+ "vision_model.encoder.layers.0.norm1.bias": "model-00001-of-00004.safetensors",
254
+ "vision_model.encoder.layers.0.norm1.weight": "model-00001-of-00004.safetensors",
255
+ "vision_model.encoder.layers.0.norm2.bias": "model-00001-of-00004.safetensors",
256
+ "vision_model.encoder.layers.0.norm2.weight": "model-00001-of-00004.safetensors",
257
+ "vision_model.encoder.layers.1.attn.proj.bias": "model-00001-of-00004.safetensors",
258
+ "vision_model.encoder.layers.1.attn.proj.weight": "model-00001-of-00004.safetensors",
259
+ "vision_model.encoder.layers.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
260
+ "vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
261
+ "vision_model.encoder.layers.1.ls1": "model-00001-of-00004.safetensors",
262
+ "vision_model.encoder.layers.1.ls2": "model-00001-of-00004.safetensors",
263
+ "vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
264
+ "vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
265
+ "vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
266
+ "vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
267
+ "vision_model.encoder.layers.1.norm1.bias": "model-00001-of-00004.safetensors",
268
+ "vision_model.encoder.layers.1.norm1.weight": "model-00001-of-00004.safetensors",
269
+ "vision_model.encoder.layers.1.norm2.bias": "model-00001-of-00004.safetensors",
270
+ "vision_model.encoder.layers.1.norm2.weight": "model-00001-of-00004.safetensors",
271
+ "vision_model.encoder.layers.10.attn.proj.bias": "model-00001-of-00004.safetensors",
272
+ "vision_model.encoder.layers.10.attn.proj.weight": "model-00001-of-00004.safetensors",
273
+ "vision_model.encoder.layers.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
274
+ "vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
275
+ "vision_model.encoder.layers.10.ls1": "model-00001-of-00004.safetensors",
276
+ "vision_model.encoder.layers.10.ls2": "model-00001-of-00004.safetensors",
277
+ "vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
278
+ "vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
279
+ "vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
280
+ "vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
281
+ "vision_model.encoder.layers.10.norm1.bias": "model-00001-of-00004.safetensors",
282
+ "vision_model.encoder.layers.10.norm1.weight": "model-00001-of-00004.safetensors",
283
+ "vision_model.encoder.layers.10.norm2.bias": "model-00001-of-00004.safetensors",
284
+ "vision_model.encoder.layers.10.norm2.weight": "model-00001-of-00004.safetensors",
285
+ "vision_model.encoder.layers.11.attn.proj.bias": "model-00001-of-00004.safetensors",
286
+ "vision_model.encoder.layers.11.attn.proj.weight": "model-00001-of-00004.safetensors",
287
+ "vision_model.encoder.layers.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
288
+ "vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
289
+ "vision_model.encoder.layers.11.ls1": "model-00001-of-00004.safetensors",
290
+ "vision_model.encoder.layers.11.ls2": "model-00001-of-00004.safetensors",
291
+ "vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
292
+ "vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
293
+ "vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
294
+ "vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
295
+ "vision_model.encoder.layers.11.norm1.bias": "model-00001-of-00004.safetensors",
296
+ "vision_model.encoder.layers.11.norm1.weight": "model-00001-of-00004.safetensors",
297
+ "vision_model.encoder.layers.11.norm2.bias": "model-00001-of-00004.safetensors",
298
+ "vision_model.encoder.layers.11.norm2.weight": "model-00001-of-00004.safetensors",
299
+ "vision_model.encoder.layers.12.attn.proj.bias": "model-00001-of-00004.safetensors",
300
+ "vision_model.encoder.layers.12.attn.proj.weight": "model-00001-of-00004.safetensors",
301
+ "vision_model.encoder.layers.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
302
+ "vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
303
+ "vision_model.encoder.layers.12.ls1": "model-00001-of-00004.safetensors",
304
+ "vision_model.encoder.layers.12.ls2": "model-00001-of-00004.safetensors",
305
+ "vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
306
+ "vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
307
+ "vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
308
+ "vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
309
+ "vision_model.encoder.layers.12.norm1.bias": "model-00001-of-00004.safetensors",
310
+ "vision_model.encoder.layers.12.norm1.weight": "model-00001-of-00004.safetensors",
311
+ "vision_model.encoder.layers.12.norm2.bias": "model-00001-of-00004.safetensors",
312
+ "vision_model.encoder.layers.12.norm2.weight": "model-00001-of-00004.safetensors",
313
+ "vision_model.encoder.layers.13.attn.proj.bias": "model-00001-of-00004.safetensors",
314
+ "vision_model.encoder.layers.13.attn.proj.weight": "model-00001-of-00004.safetensors",
315
+ "vision_model.encoder.layers.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
316
+ "vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
317
+ "vision_model.encoder.layers.13.ls1": "model-00001-of-00004.safetensors",
318
+ "vision_model.encoder.layers.13.ls2": "model-00001-of-00004.safetensors",
319
+ "vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
320
+ "vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
321
+ "vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
322
+ "vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
323
+ "vision_model.encoder.layers.13.norm1.bias": "model-00001-of-00004.safetensors",
324
+ "vision_model.encoder.layers.13.norm1.weight": "model-00001-of-00004.safetensors",
325
+ "vision_model.encoder.layers.13.norm2.bias": "model-00001-of-00004.safetensors",
326
+ "vision_model.encoder.layers.13.norm2.weight": "model-00001-of-00004.safetensors",
327
+ "vision_model.encoder.layers.14.attn.proj.bias": "model-00001-of-00004.safetensors",
328
+ "vision_model.encoder.layers.14.attn.proj.weight": "model-00001-of-00004.safetensors",
329
+ "vision_model.encoder.layers.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
330
+ "vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
331
+ "vision_model.encoder.layers.14.ls1": "model-00001-of-00004.safetensors",
332
+ "vision_model.encoder.layers.14.ls2": "model-00001-of-00004.safetensors",
333
+ "vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
334
+ "vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
335
+ "vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
336
+ "vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
337
+ "vision_model.encoder.layers.14.norm1.bias": "model-00001-of-00004.safetensors",
338
+ "vision_model.encoder.layers.14.norm1.weight": "model-00001-of-00004.safetensors",
339
+ "vision_model.encoder.layers.14.norm2.bias": "model-00001-of-00004.safetensors",
340
+ "vision_model.encoder.layers.14.norm2.weight": "model-00001-of-00004.safetensors",
341
+ "vision_model.encoder.layers.15.attn.proj.bias": "model-00001-of-00004.safetensors",
342
+ "vision_model.encoder.layers.15.attn.proj.weight": "model-00001-of-00004.safetensors",
343
+ "vision_model.encoder.layers.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
344
+ "vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
345
+ "vision_model.encoder.layers.15.ls1": "model-00001-of-00004.safetensors",
346
+ "vision_model.encoder.layers.15.ls2": "model-00001-of-00004.safetensors",
347
+ "vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
348
+ "vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
349
+ "vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
350
+ "vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
351
+ "vision_model.encoder.layers.15.norm1.bias": "model-00001-of-00004.safetensors",
352
+ "vision_model.encoder.layers.15.norm1.weight": "model-00001-of-00004.safetensors",
353
+ "vision_model.encoder.layers.15.norm2.bias": "model-00001-of-00004.safetensors",
354
+ "vision_model.encoder.layers.15.norm2.weight": "model-00001-of-00004.safetensors",
355
+ "vision_model.encoder.layers.16.attn.proj.bias": "model-00001-of-00004.safetensors",
356
+ "vision_model.encoder.layers.16.attn.proj.weight": "model-00001-of-00004.safetensors",
357
+ "vision_model.encoder.layers.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
358
+ "vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
359
+ "vision_model.encoder.layers.16.ls1": "model-00001-of-00004.safetensors",
360
+ "vision_model.encoder.layers.16.ls2": "model-00001-of-00004.safetensors",
361
+ "vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
362
+ "vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
363
+ "vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
364
+ "vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
365
+ "vision_model.encoder.layers.16.norm1.bias": "model-00001-of-00004.safetensors",
366
+ "vision_model.encoder.layers.16.norm1.weight": "model-00001-of-00004.safetensors",
367
+ "vision_model.encoder.layers.16.norm2.bias": "model-00001-of-00004.safetensors",
368
+ "vision_model.encoder.layers.16.norm2.weight": "model-00001-of-00004.safetensors",
369
+ "vision_model.encoder.layers.17.attn.proj.bias": "model-00001-of-00004.safetensors",
370
+ "vision_model.encoder.layers.17.attn.proj.weight": "model-00001-of-00004.safetensors",
371
+ "vision_model.encoder.layers.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
372
+ "vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
373
+ "vision_model.encoder.layers.17.ls1": "model-00001-of-00004.safetensors",
374
+ "vision_model.encoder.layers.17.ls2": "model-00001-of-00004.safetensors",
375
+ "vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
376
+ "vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
377
+ "vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
378
+ "vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
379
+ "vision_model.encoder.layers.17.norm1.bias": "model-00001-of-00004.safetensors",
380
+ "vision_model.encoder.layers.17.norm1.weight": "model-00001-of-00004.safetensors",
381
+ "vision_model.encoder.layers.17.norm2.bias": "model-00001-of-00004.safetensors",
382
+ "vision_model.encoder.layers.17.norm2.weight": "model-00001-of-00004.safetensors",
383
+ "vision_model.encoder.layers.18.attn.proj.bias": "model-00001-of-00004.safetensors",
384
+ "vision_model.encoder.layers.18.attn.proj.weight": "model-00001-of-00004.safetensors",
385
+ "vision_model.encoder.layers.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
386
+ "vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
387
+ "vision_model.encoder.layers.18.ls1": "model-00001-of-00004.safetensors",
388
+ "vision_model.encoder.layers.18.ls2": "model-00001-of-00004.safetensors",
389
+ "vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
390
+ "vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
391
+ "vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
392
+ "vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
393
+ "vision_model.encoder.layers.18.norm1.bias": "model-00001-of-00004.safetensors",
394
+ "vision_model.encoder.layers.18.norm1.weight": "model-00001-of-00004.safetensors",
395
+ "vision_model.encoder.layers.18.norm2.bias": "model-00001-of-00004.safetensors",
396
+ "vision_model.encoder.layers.18.norm2.weight": "model-00001-of-00004.safetensors",
397
+ "vision_model.encoder.layers.19.attn.proj.bias": "model-00001-of-00004.safetensors",
398
+ "vision_model.encoder.layers.19.attn.proj.weight": "model-00001-of-00004.safetensors",
399
+ "vision_model.encoder.layers.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
400
+ "vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
401
+ "vision_model.encoder.layers.19.ls1": "model-00001-of-00004.safetensors",
402
+ "vision_model.encoder.layers.19.ls2": "model-00001-of-00004.safetensors",
403
+ "vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
404
+ "vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
405
+ "vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
406
+ "vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
407
+ "vision_model.encoder.layers.19.norm1.bias": "model-00001-of-00004.safetensors",
408
+ "vision_model.encoder.layers.19.norm1.weight": "model-00001-of-00004.safetensors",
409
+ "vision_model.encoder.layers.19.norm2.bias": "model-00001-of-00004.safetensors",
410
+ "vision_model.encoder.layers.19.norm2.weight": "model-00001-of-00004.safetensors",
411
+ "vision_model.encoder.layers.2.attn.proj.bias": "model-00001-of-00004.safetensors",
412
+ "vision_model.encoder.layers.2.attn.proj.weight": "model-00001-of-00004.safetensors",
413
+ "vision_model.encoder.layers.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
414
+ "vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
415
+ "vision_model.encoder.layers.2.ls1": "model-00001-of-00004.safetensors",
416
+ "vision_model.encoder.layers.2.ls2": "model-00001-of-00004.safetensors",
417
+ "vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
418
+ "vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
419
+ "vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
420
+ "vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
421
+ "vision_model.encoder.layers.2.norm1.bias": "model-00001-of-00004.safetensors",
422
+ "vision_model.encoder.layers.2.norm1.weight": "model-00001-of-00004.safetensors",
423
+ "vision_model.encoder.layers.2.norm2.bias": "model-00001-of-00004.safetensors",
424
+ "vision_model.encoder.layers.2.norm2.weight": "model-00001-of-00004.safetensors",
425
+ "vision_model.encoder.layers.20.attn.proj.bias": "model-00001-of-00004.safetensors",
426
+ "vision_model.encoder.layers.20.attn.proj.weight": "model-00001-of-00004.safetensors",
427
+ "vision_model.encoder.layers.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
428
+ "vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
429
+ "vision_model.encoder.layers.20.ls1": "model-00001-of-00004.safetensors",
430
+ "vision_model.encoder.layers.20.ls2": "model-00001-of-00004.safetensors",
431
+ "vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
432
+ "vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
433
+ "vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
434
+ "vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
435
+ "vision_model.encoder.layers.20.norm1.bias": "model-00001-of-00004.safetensors",
436
+ "vision_model.encoder.layers.20.norm1.weight": "model-00001-of-00004.safetensors",
437
+ "vision_model.encoder.layers.20.norm2.bias": "model-00001-of-00004.safetensors",
438
+ "vision_model.encoder.layers.20.norm2.weight": "model-00001-of-00004.safetensors",
439
+ "vision_model.encoder.layers.21.attn.proj.bias": "model-00001-of-00004.safetensors",
440
+ "vision_model.encoder.layers.21.attn.proj.weight": "model-00001-of-00004.safetensors",
441
+ "vision_model.encoder.layers.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
442
+ "vision_model.encoder.layers.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
443
+ "vision_model.encoder.layers.21.ls1": "model-00001-of-00004.safetensors",
444
+ "vision_model.encoder.layers.21.ls2": "model-00001-of-00004.safetensors",
445
+ "vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
446
+ "vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
447
+ "vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
448
+ "vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
449
+ "vision_model.encoder.layers.21.norm1.bias": "model-00001-of-00004.safetensors",
450
+ "vision_model.encoder.layers.21.norm1.weight": "model-00001-of-00004.safetensors",
451
+ "vision_model.encoder.layers.21.norm2.bias": "model-00001-of-00004.safetensors",
452
+ "vision_model.encoder.layers.21.norm2.weight": "model-00001-of-00004.safetensors",
453
+ "vision_model.encoder.layers.22.attn.proj.bias": "model-00001-of-00004.safetensors",
454
+ "vision_model.encoder.layers.22.attn.proj.weight": "model-00001-of-00004.safetensors",
455
+ "vision_model.encoder.layers.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
456
+ "vision_model.encoder.layers.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
457
+ "vision_model.encoder.layers.22.ls1": "model-00001-of-00004.safetensors",
458
+ "vision_model.encoder.layers.22.ls2": "model-00001-of-00004.safetensors",
459
+ "vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
460
+ "vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
461
+ "vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
462
+ "vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
463
+ "vision_model.encoder.layers.22.norm1.bias": "model-00001-of-00004.safetensors",
464
+ "vision_model.encoder.layers.22.norm1.weight": "model-00001-of-00004.safetensors",
465
+ "vision_model.encoder.layers.22.norm2.bias": "model-00001-of-00004.safetensors",
466
+ "vision_model.encoder.layers.22.norm2.weight": "model-00001-of-00004.safetensors",
467
+ "vision_model.encoder.layers.23.attn.proj.bias": "model-00001-of-00004.safetensors",
468
+ "vision_model.encoder.layers.23.attn.proj.weight": "model-00001-of-00004.safetensors",
469
+ "vision_model.encoder.layers.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
470
+ "vision_model.encoder.layers.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
471
+ "vision_model.encoder.layers.23.ls1": "model-00001-of-00004.safetensors",
472
+ "vision_model.encoder.layers.23.ls2": "model-00001-of-00004.safetensors",
473
+ "vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
474
+ "vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
475
+ "vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
476
+ "vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
477
+ "vision_model.encoder.layers.23.norm1.bias": "model-00001-of-00004.safetensors",
478
+ "vision_model.encoder.layers.23.norm1.weight": "model-00001-of-00004.safetensors",
479
+ "vision_model.encoder.layers.23.norm2.bias": "model-00001-of-00004.safetensors",
480
+ "vision_model.encoder.layers.23.norm2.weight": "model-00001-of-00004.safetensors",
481
+ "vision_model.encoder.layers.3.attn.proj.bias": "model-00001-of-00004.safetensors",
482
+ "vision_model.encoder.layers.3.attn.proj.weight": "model-00001-of-00004.safetensors",
483
+ "vision_model.encoder.layers.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
484
+ "vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
485
+ "vision_model.encoder.layers.3.ls1": "model-00001-of-00004.safetensors",
486
+ "vision_model.encoder.layers.3.ls2": "model-00001-of-00004.safetensors",
487
+ "vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
488
+ "vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
489
+ "vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
490
+ "vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
491
+ "vision_model.encoder.layers.3.norm1.bias": "model-00001-of-00004.safetensors",
492
+ "vision_model.encoder.layers.3.norm1.weight": "model-00001-of-00004.safetensors",
493
+ "vision_model.encoder.layers.3.norm2.bias": "model-00001-of-00004.safetensors",
494
+ "vision_model.encoder.layers.3.norm2.weight": "model-00001-of-00004.safetensors",
495
+ "vision_model.encoder.layers.4.attn.proj.bias": "model-00001-of-00004.safetensors",
496
+ "vision_model.encoder.layers.4.attn.proj.weight": "model-00001-of-00004.safetensors",
497
+ "vision_model.encoder.layers.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
498
+ "vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
499
+ "vision_model.encoder.layers.4.ls1": "model-00001-of-00004.safetensors",
500
+ "vision_model.encoder.layers.4.ls2": "model-00001-of-00004.safetensors",
501
+ "vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
502
+ "vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
503
+ "vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
504
+ "vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
505
+ "vision_model.encoder.layers.4.norm1.bias": "model-00001-of-00004.safetensors",
506
+ "vision_model.encoder.layers.4.norm1.weight": "model-00001-of-00004.safetensors",
507
+ "vision_model.encoder.layers.4.norm2.bias": "model-00001-of-00004.safetensors",
508
+ "vision_model.encoder.layers.4.norm2.weight": "model-00001-of-00004.safetensors",
509
+ "vision_model.encoder.layers.5.attn.proj.bias": "model-00001-of-00004.safetensors",
510
+ "vision_model.encoder.layers.5.attn.proj.weight": "model-00001-of-00004.safetensors",
511
+ "vision_model.encoder.layers.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
512
+ "vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
513
+ "vision_model.encoder.layers.5.ls1": "model-00001-of-00004.safetensors",
514
+ "vision_model.encoder.layers.5.ls2": "model-00001-of-00004.safetensors",
515
+ "vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
516
+ "vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
517
+ "vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
518
+ "vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
519
+ "vision_model.encoder.layers.5.norm1.bias": "model-00001-of-00004.safetensors",
520
+ "vision_model.encoder.layers.5.norm1.weight": "model-00001-of-00004.safetensors",
521
+ "vision_model.encoder.layers.5.norm2.bias": "model-00001-of-00004.safetensors",
522
+ "vision_model.encoder.layers.5.norm2.weight": "model-00001-of-00004.safetensors",
523
+ "vision_model.encoder.layers.6.attn.proj.bias": "model-00001-of-00004.safetensors",
524
+ "vision_model.encoder.layers.6.attn.proj.weight": "model-00001-of-00004.safetensors",
525
+ "vision_model.encoder.layers.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
526
+ "vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
527
+ "vision_model.encoder.layers.6.ls1": "model-00001-of-00004.safetensors",
528
+ "vision_model.encoder.layers.6.ls2": "model-00001-of-00004.safetensors",
529
+ "vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
530
+ "vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
531
+ "vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
532
+ "vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
533
+ "vision_model.encoder.layers.6.norm1.bias": "model-00001-of-00004.safetensors",
534
+ "vision_model.encoder.layers.6.norm1.weight": "model-00001-of-00004.safetensors",
535
+ "vision_model.encoder.layers.6.norm2.bias": "model-00001-of-00004.safetensors",
536
+ "vision_model.encoder.layers.6.norm2.weight": "model-00001-of-00004.safetensors",
537
+ "vision_model.encoder.layers.7.attn.proj.bias": "model-00001-of-00004.safetensors",
538
+ "vision_model.encoder.layers.7.attn.proj.weight": "model-00001-of-00004.safetensors",
539
+ "vision_model.encoder.layers.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
540
+ "vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
541
+ "vision_model.encoder.layers.7.ls1": "model-00001-of-00004.safetensors",
542
+ "vision_model.encoder.layers.7.ls2": "model-00001-of-00004.safetensors",
543
+ "vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
544
+ "vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
545
+ "vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
546
+ "vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
547
+ "vision_model.encoder.layers.7.norm1.bias": "model-00001-of-00004.safetensors",
548
+ "vision_model.encoder.layers.7.norm1.weight": "model-00001-of-00004.safetensors",
549
+ "vision_model.encoder.layers.7.norm2.bias": "model-00001-of-00004.safetensors",
550
+ "vision_model.encoder.layers.7.norm2.weight": "model-00001-of-00004.safetensors",
551
+ "vision_model.encoder.layers.8.attn.proj.bias": "model-00001-of-00004.safetensors",
552
+ "vision_model.encoder.layers.8.attn.proj.weight": "model-00001-of-00004.safetensors",
553
+ "vision_model.encoder.layers.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
554
+ "vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
555
+ "vision_model.encoder.layers.8.ls1": "model-00001-of-00004.safetensors",
556
+ "vision_model.encoder.layers.8.ls2": "model-00001-of-00004.safetensors",
557
+ "vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
558
+ "vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
559
+ "vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
560
+ "vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
561
+ "vision_model.encoder.layers.8.norm1.bias": "model-00001-of-00004.safetensors",
562
+ "vision_model.encoder.layers.8.norm1.weight": "model-00001-of-00004.safetensors",
563
+ "vision_model.encoder.layers.8.norm2.bias": "model-00001-of-00004.safetensors",
564
+ "vision_model.encoder.layers.8.norm2.weight": "model-00001-of-00004.safetensors",
565
+ "vision_model.encoder.layers.9.attn.proj.bias": "model-00001-of-00004.safetensors",
566
+ "vision_model.encoder.layers.9.attn.proj.weight": "model-00001-of-00004.safetensors",
567
+ "vision_model.encoder.layers.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
568
+ "vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
569
+ "vision_model.encoder.layers.9.ls1": "model-00001-of-00004.safetensors",
570
+ "vision_model.encoder.layers.9.ls2": "model-00001-of-00004.safetensors",
571
+ "vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
572
+ "vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
573
+ "vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
574
+ "vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
575
+ "vision_model.encoder.layers.9.norm1.bias": "model-00001-of-00004.safetensors",
576
+ "vision_model.encoder.layers.9.norm1.weight": "model-00001-of-00004.safetensors",
577
+ "vision_model.encoder.layers.9.norm2.bias": "model-00001-of-00004.safetensors",
578
+ "vision_model.encoder.layers.9.norm2.weight": "model-00001-of-00004.safetensors"
579
+ }
580
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|action_start|>",
6
+ "<|action_end|>",
7
+ "<|interpreter|>",
8
+ "<|plugin|>",
9
+ "<img>",
10
+ "</img>",
11
+ "<IMG_CONTEXT>",
12
+ "<quad>",
13
+ "</quad>",
14
+ "<ref>",
15
+ "</ref>",
16
+ "<box>",
17
+ "</box>"
18
+ ],
19
+ "bos_token": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "eos_token": {
27
+ "content": "</s>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "pad_token": {
34
+ "content": "</s>",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ },
40
+ "unk_token": {
41
+ "content": "<unk>",
42
+ "lstrip": false,
43
+ "normalized": false,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ }
47
+ }
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]
tokenization_internlm2_fast.py ADDED
@@ -0,0 +1,211 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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_fast.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 Fast class for InternLM."""
18
+ import os
19
+ from shutil import copyfile
20
+ from typing import Any, Dict, Optional, Tuple
21
+
22
+ from tokenizers import Tokenizer, decoders, normalizers, processors
23
+ from tokenizers.models import BPE
24
+ from transformers.convert_slow_tokenizer import (SLOW_TO_FAST_CONVERTERS,
25
+ SentencePieceExtractor,
26
+ SpmConverter)
27
+ from transformers.tokenization_utils_fast import PreTrainedTokenizerFast
28
+ from transformers.utils import logging
29
+
30
+ from .tokenization_internlm2 import InternLM2Tokenizer
31
+
32
+ logger = logging.get_logger(__name__)
33
+
34
+ VOCAB_FILES_NAMES = {'vocab_file': './tokenizer.model'}
35
+
36
+
37
+ # Modified from transformers.convert_slow_tokenizer.LlamaConverter
38
+ class InternLM2Converter(SpmConverter):
39
+ handle_byte_fallback = True
40
+
41
+ def vocab(self, proto):
42
+ vocab = [
43
+ ('<unk>', 0.0),
44
+ ('<s>', 0.0),
45
+ ('</s>', 0.0),
46
+ ]
47
+ vocab += [(piece.piece, piece.score) for piece in proto.pieces[3:]]
48
+ return vocab
49
+
50
+ def unk_id(self, proto):
51
+ unk_id = 0
52
+ return unk_id
53
+
54
+ def decoder(self, replacement, add_prefix_space):
55
+ return decoders.Sequence(
56
+ [
57
+ decoders.Replace('▁', ' '),
58
+ decoders.ByteFallback(),
59
+ decoders.Fuse(),
60
+ decoders.Strip(content=' ', left=1),
61
+ ]
62
+ )
63
+
64
+ def tokenizer(self, proto):
65
+ model_type = proto.trainer_spec.model_type
66
+ vocab_scores = self.vocab(proto)
67
+ # special tokens
68
+ added_tokens = self.original_tokenizer.added_tokens_decoder
69
+ for i in range(len(vocab_scores)):
70
+ piece, score = vocab_scores[i]
71
+ if i in added_tokens:
72
+ vocab_scores[i] = (added_tokens[i].content, score)
73
+ if model_type == 1:
74
+ raise RuntimeError('InternLM2 is supposed to be a BPE model!')
75
+
76
+ elif model_type == 2:
77
+ _, merges = SentencePieceExtractor(self.original_tokenizer.vocab_file).extract(vocab_scores)
78
+ bpe_vocab = {word: i for i, (word, _score) in enumerate(vocab_scores)}
79
+ tokenizer = Tokenizer(
80
+ BPE(bpe_vocab, merges, unk_token=proto.trainer_spec.unk_piece, fuse_unk=True, byte_fallback=True)
81
+ )
82
+ tokenizer.add_special_tokens(
83
+ [ added_token for index, added_token in added_tokens.items()]
84
+ )
85
+ else:
86
+ raise Exception(
87
+ "You're trying to run a `Unigram` model but you're file was trained with a different algorithm"
88
+ )
89
+
90
+ return tokenizer
91
+
92
+ def normalizer(self, proto):
93
+ normalizers_list = []
94
+ if proto.normalizer_spec.add_dummy_prefix:
95
+ normalizers_list.append(normalizers.Prepend(prepend='▁'))
96
+ normalizers_list.append(normalizers.Replace(pattern=' ', content='▁'))
97
+ return normalizers.Sequence(normalizers_list)
98
+
99
+ def pre_tokenizer(self, replacement, add_prefix_space):
100
+ return None
101
+
102
+
103
+ SLOW_TO_FAST_CONVERTERS['InternLM2Tokenizer'] = InternLM2Converter
104
+
105
+
106
+ # Modified from transformers.model.llama.tokenization_llama_fast.LlamaTokenizerFast -> InternLM2TokenizerFast
107
+ class InternLM2TokenizerFast(PreTrainedTokenizerFast):
108
+ vocab_files_names = VOCAB_FILES_NAMES
109
+ slow_tokenizer_class = InternLM2Tokenizer
110
+ padding_side = 'left'
111
+ model_input_names = ['input_ids', 'attention_mask']
112
+ _auto_class = 'AutoTokenizer'
113
+
114
+ def __init__(
115
+ self,
116
+ vocab_file,
117
+ unk_token='<unk>',
118
+ bos_token='<s>',
119
+ eos_token='</s>',
120
+ pad_token='</s>',
121
+ sp_model_kwargs: Optional[Dict[str, Any]] = None,
122
+ add_bos_token=True,
123
+ add_eos_token=False,
124
+ decode_with_prefix_space=False,
125
+ clean_up_tokenization_spaces=False,
126
+ **kwargs,
127
+ ):
128
+ super().__init__(
129
+ vocab_file=vocab_file,
130
+ unk_token=unk_token,
131
+ bos_token=bos_token,
132
+ eos_token=eos_token,
133
+ pad_token=pad_token,
134
+ sp_model_kwargs=sp_model_kwargs,
135
+ add_bos_token=add_bos_token,
136
+ add_eos_token=add_eos_token,
137
+ decode_with_prefix_space=decode_with_prefix_space,
138
+ clean_up_tokenization_spaces=clean_up_tokenization_spaces,
139
+ **kwargs,
140
+ )
141
+ self._add_bos_token = add_bos_token
142
+ self._add_eos_token = add_eos_token
143
+ self.update_post_processor()
144
+ self.vocab_file = vocab_file
145
+
146
+ @property
147
+ def can_save_slow_tokenizer(self) -> bool:
148
+ return os.path.isfile(self.vocab_file) if self.vocab_file else False
149
+
150
+ def update_post_processor(self):
151
+ """
152
+ Updates the underlying post processor with the current `bos_token` and `eos_token`.
153
+ """
154
+ bos = self.bos_token
155
+ bos_token_id = self.bos_token_id
156
+ if bos is None and self.add_bos_token:
157
+ raise ValueError('add_bos_token = True but bos_token = None')
158
+
159
+ eos = self.eos_token
160
+ eos_token_id = self.eos_token_id
161
+ if eos is None and self.add_eos_token:
162
+ raise ValueError('add_eos_token = True but eos_token = None')
163
+
164
+ single = f"{(bos+':0 ') if self.add_bos_token else ''}$A:0{(' '+eos+':0') if self.add_eos_token else ''}"
165
+ pair = f"{single}{(' '+bos+':1') if self.add_bos_token else ''} $B:1{(' '+eos+':1') if self.add_eos_token else ''}"
166
+
167
+ special_tokens = []
168
+ if self.add_bos_token:
169
+ special_tokens.append((bos, bos_token_id))
170
+ if self.add_eos_token:
171
+ special_tokens.append((eos, eos_token_id))
172
+ self._tokenizer.post_processor = processors.TemplateProcessing(
173
+ single=single, pair=pair, special_tokens=special_tokens
174
+ )
175
+
176
+ @property
177
+ def add_eos_token(self):
178
+ return self._add_eos_token
179
+
180
+ @property
181
+ def add_bos_token(self):
182
+ return self._add_bos_token
183
+
184
+ @add_eos_token.setter
185
+ def add_eos_token(self, value):
186
+ self._add_eos_token = value
187
+ self.update_post_processor()
188
+
189
+ @add_bos_token.setter
190
+ def add_bos_token(self, value):
191
+ self._add_bos_token = value
192
+ self.update_post_processor()
193
+
194
+ def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
195
+ if not self.can_save_slow_tokenizer:
196
+ raise ValueError(
197
+ 'Your fast tokenizer does not have the necessary information to save the vocabulary for a slow '
198
+ 'tokenizer.'
199
+ )
200
+
201
+ if not os.path.isdir(save_directory):
202
+ logger.error(f'Vocabulary path ({save_directory}) should be a directory')
203
+ return
204
+ out_vocab_file = os.path.join(
205
+ save_directory, (filename_prefix + '-' if filename_prefix else '') + VOCAB_FILES_NAMES['vocab_file']
206
+ )
207
+
208
+ if os.path.abspath(self.vocab_file) != os.path.abspath(out_vocab_file):
209
+ copyfile(self.vocab_file, out_vocab_file)
210
+
211
+ return (out_vocab_file,)
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "92529": {
30
+ "content": "</box>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "92530": {
38
+ "content": "<box>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "92531": {
46
+ "content": "</ref>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "92532": {
54
+ "content": "<ref>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "92533": {
62
+ "content": "</quad>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "92534": {
70
+ "content": "<quad>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "92535": {
78
+ "content": "<IMG_CONTEXT>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "92536": {
86
+ "content": "</img>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "92537": {
94
+ "content": "<img>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "92538": {
102
+ "content": "<|plugin|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "92539": {
110
+ "content": "<|interpreter|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "92540": {
118
+ "content": "<|action_end|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "92541": {
126
+ "content": "<|action_start|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "92542": {
134
+ "content": "<|im_end|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "92543": {
142
+ "content": "<|im_start|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ }
149
+ },
150
+ "additional_special_tokens": [
151
+ "<|im_start|>",
152
+ "<|im_end|>",
153
+ "<|action_start|>",
154
+ "<|action_end|>",
155
+ "<|interpreter|>",
156
+ "<|plugin|>",
157
+ "<img>",
158
+ "</img>",
159
+ "<IMG_CONTEXT>",
160
+ "<quad>",
161
+ "</quad>",
162
+ "<ref>",
163
+ "</ref>",
164
+ "<box>",
165
+ "</box>"
166
+ ],
167
+ "auto_map": {
168
+ "AutoTokenizer": [
169
+ "tokenization_internlm2.InternLM2Tokenizer",
170
+ "tokenization_internlm2_fast.InternLM2TokenizerFast"
171
+ ]
172
+ },
173
+ "bos_token": "<s>",
174
+ "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 %}",
175
+ "clean_up_tokenization_spaces": false,
176
+ "decode_with_prefix_space": false,
177
+ "eos_token": "</s>",
178
+ "model_max_length": 16384,
179
+ "pad_token": "</s>",
180
+ "sp_model_kwargs": null,
181
+ "tokenizer_class": "InternLM2Tokenizer",
182
+ "unk_token": "<unk>"
183
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.2210330774939678,
4
+ "train_runtime": 11823.142,
5
+ "train_samples": 100012,
6
+ "train_samples_per_second": 8.459,
7
+ "train_steps_per_second": 0.132
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d868e57b8dc827fefc03e9026c16d934180ea8975c4352b35a8853a22625fe2
3
+ size 6075