Jackbrocp commited on
Commit
0a151a4
1 Parent(s): 413edf7

Upload chemvlm8b_1_stage_09_09 with huggingface_hub

Browse files
Files changed (1) hide show
  1. chemvlm8b_1_stage_09_09 +201 -0
chemvlm8b_1_stage_09_09 ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "/home/bingxing2/ailab/wangxunzhi/work/InternVL-main/internvl_chat/work_dirs/new_1_stage/checkpoint-12400",
4
+ "architectures": [
5
+ "InternVLChatModel"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_internvl_chat.InternVLChatConfig",
9
+ "AutoModel": "modeling_internvl_chat.InternVLChatModel",
10
+ "AutoModelForCausalLM": "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_5-7b-chat",
17
+ "add_cross_attention": false,
18
+ "architectures": [
19
+ "InternLM2ForCausalLM"
20
+ ],
21
+ "attn_implementation": "eager",
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": 4096,
45
+ "id2label": {
46
+ "0": "LABEL_0",
47
+ "1": "LABEL_1"
48
+ },
49
+ "initializer_range": 0.02,
50
+ "intermediate_size": 14336,
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": 32,
64
+ "num_beam_groups": 1,
65
+ "num_beams": 1,
66
+ "num_hidden_layers": 32,
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
+ "pretraining_tp": 1,
75
+ "problem_type": null,
76
+ "pruned_heads": {},
77
+ "remove_invalid_values": false,
78
+ "repetition_penalty": 1.0,
79
+ "return_dict": true,
80
+ "return_dict_in_generate": false,
81
+ "rms_norm_eps": 1e-05,
82
+ "rope_scaling": {
83
+ "factor": 2.0,
84
+ "type": "dynamic"
85
+ },
86
+ "rope_theta": 1000000,
87
+ "sep_token_id": null,
88
+ "suppress_tokens": null,
89
+ "task_specific_params": null,
90
+ "temperature": 1.0,
91
+ "tf_legacy_loss": false,
92
+ "tie_encoder_decoder": false,
93
+ "tie_word_embeddings": false,
94
+ "tokenizer_class": null,
95
+ "top_k": 50,
96
+ "top_p": 1.0,
97
+ "torch_dtype": "bfloat16",
98
+ "torchscript": false,
99
+ "transformers_version": "4.39.3",
100
+ "typical_p": 1.0,
101
+ "use_bfloat16": true,
102
+ "use_cache": false,
103
+ "vocab_size": 92553
104
+ },
105
+ "max_dynamic_patch": 12,
106
+ "min_dynamic_patch": 1,
107
+ "model_type": "internvl_chat",
108
+ "pad2square": false,
109
+ "ps_version": "'v2'",
110
+ "select_layer": -1,
111
+ "template": "internlm2-chat",
112
+ "torch_dtype": "bfloat16",
113
+ "transformers_version": null,
114
+ "use_backbone_lora": 0,
115
+ "use_llm_lora": 0,
116
+ "use_thumbnail": true,
117
+ "vision_config": {
118
+ "_name_or_path": "",
119
+ "add_cross_attention": false,
120
+ "architectures": [
121
+ "InternVisionModel"
122
+ ],
123
+ "attention_dropout": 0.0,
124
+ "bad_words_ids": null,
125
+ "begin_suppress_tokens": null,
126
+ "bos_token_id": null,
127
+ "chunk_size_feed_forward": 0,
128
+ "cross_attention_hidden_size": null,
129
+ "decoder_start_token_id": null,
130
+ "diversity_penalty": 0.0,
131
+ "do_sample": false,
132
+ "drop_path_rate": 0.0,
133
+ "dropout": 0.0,
134
+ "early_stopping": false,
135
+ "encoder_no_repeat_ngram_size": 0,
136
+ "eos_token_id": null,
137
+ "exponential_decay_length_penalty": null,
138
+ "finetuning_task": null,
139
+ "forced_bos_token_id": null,
140
+ "forced_eos_token_id": null,
141
+ "hidden_act": "gelu",
142
+ "hidden_size": 1024,
143
+ "id2label": {
144
+ "0": "LABEL_0",
145
+ "1": "LABEL_1"
146
+ },
147
+ "image_size": 448,
148
+ "initializer_factor": 1.0,
149
+ "initializer_range": 0.02,
150
+ "intermediate_size": 4096,
151
+ "is_decoder": false,
152
+ "is_encoder_decoder": false,
153
+ "label2id": {
154
+ "LABEL_0": 0,
155
+ "LABEL_1": 1
156
+ },
157
+ "layer_norm_eps": 1e-06,
158
+ "length_penalty": 1.0,
159
+ "max_length": 20,
160
+ "min_length": 0,
161
+ "model_type": "intern_vit_6b",
162
+ "no_repeat_ngram_size": 0,
163
+ "norm_type": "layer_norm",
164
+ "num_attention_heads": 16,
165
+ "num_beam_groups": 1,
166
+ "num_beams": 1,
167
+ "num_channels": 3,
168
+ "num_hidden_layers": 24,
169
+ "num_return_sequences": 1,
170
+ "output_attentions": false,
171
+ "output_hidden_states": false,
172
+ "output_scores": false,
173
+ "pad_token_id": null,
174
+ "patch_size": 14,
175
+ "prefix": null,
176
+ "problem_type": null,
177
+ "pruned_heads": {},
178
+ "qk_normalization": false,
179
+ "qkv_bias": true,
180
+ "remove_invalid_values": false,
181
+ "repetition_penalty": 1.0,
182
+ "return_dict": true,
183
+ "return_dict_in_generate": false,
184
+ "sep_token_id": null,
185
+ "suppress_tokens": null,
186
+ "task_specific_params": null,
187
+ "temperature": 1.0,
188
+ "tf_legacy_loss": false,
189
+ "tie_encoder_decoder": false,
190
+ "tie_word_embeddings": true,
191
+ "tokenizer_class": null,
192
+ "top_k": 50,
193
+ "top_p": 1.0,
194
+ "torch_dtype": "bfloat16",
195
+ "torchscript": false,
196
+ "transformers_version": "4.39.3",
197
+ "typical_p": 1.0,
198
+ "use_bfloat16": true,
199
+ "use_flash_attn": true
200
+ }
201
+ }