GenuineWWD commited on
Commit
febc3de
·
verified ·
1 Parent(s): bb1a6d9

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +200 -0
config.json ADDED
@@ -0,0 +1,200 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "/mnt/afs/wangjiahao/workspace/hf_home/InternVL2_5-38B",
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
+ "hidden_size": 5120,
16
+ "llm_config": {
17
+ "_attn_implementation_autoset": true,
18
+ "_name_or_path": "Qwen/Qwen2.5-32B-Instruct",
19
+ "add_cross_attention": false,
20
+ "architectures": [
21
+ "Qwen2ForCausalLM"
22
+ ],
23
+ "attention_dropout": 0.0,
24
+ "attn_implementation": "flash_attention_2",
25
+ "bad_words_ids": null,
26
+ "begin_suppress_tokens": null,
27
+ "bos_token_id": 151643,
28
+ "chunk_size_feed_forward": 0,
29
+ "cross_attention_hidden_size": null,
30
+ "decoder_start_token_id": null,
31
+ "diversity_penalty": 0.0,
32
+ "do_sample": false,
33
+ "early_stopping": false,
34
+ "encoder_no_repeat_ngram_size": 0,
35
+ "eos_token_id": 151645,
36
+ "exponential_decay_length_penalty": null,
37
+ "finetuning_task": null,
38
+ "forced_bos_token_id": null,
39
+ "forced_eos_token_id": null,
40
+ "hidden_act": "silu",
41
+ "hidden_size": 5120,
42
+ "id2label": {
43
+ "0": "LABEL_0",
44
+ "1": "LABEL_1"
45
+ },
46
+ "initializer_range": 0.02,
47
+ "intermediate_size": 27648,
48
+ "is_decoder": false,
49
+ "is_encoder_decoder": false,
50
+ "label2id": {
51
+ "LABEL_0": 0,
52
+ "LABEL_1": 1
53
+ },
54
+ "length_penalty": 1.0,
55
+ "max_length": 20,
56
+ "max_position_embeddings": 32768,
57
+ "max_window_layers": 70,
58
+ "min_length": 0,
59
+ "model_type": "qwen2",
60
+ "no_repeat_ngram_size": 0,
61
+ "num_attention_heads": 40,
62
+ "num_beam_groups": 1,
63
+ "num_beams": 1,
64
+ "num_hidden_layers": 64,
65
+ "num_key_value_heads": 8,
66
+ "num_return_sequences": 1,
67
+ "output_attentions": false,
68
+ "output_hidden_states": false,
69
+ "output_scores": false,
70
+ "pad_token_id": null,
71
+ "prefix": null,
72
+ "problem_type": null,
73
+ "pruned_heads": {},
74
+ "remove_invalid_values": false,
75
+ "repetition_penalty": 1.0,
76
+ "return_dict": true,
77
+ "return_dict_in_generate": false,
78
+ "rms_norm_eps": 1e-06,
79
+ "rope_scaling": null,
80
+ "rope_theta": 1000000.0,
81
+ "sep_token_id": null,
82
+ "sliding_window": null,
83
+ "suppress_tokens": null,
84
+ "task_specific_params": null,
85
+ "temperature": 1.0,
86
+ "tf_legacy_loss": false,
87
+ "tie_encoder_decoder": false,
88
+ "tie_word_embeddings": false,
89
+ "tokenizer_class": null,
90
+ "top_k": 50,
91
+ "top_p": 1.0,
92
+ "torch_dtype": "bfloat16",
93
+ "torchscript": false,
94
+ "transformers_version": "4.48.3",
95
+ "typical_p": 1.0,
96
+ "use_bfloat16": true,
97
+ "use_cache": true,
98
+ "use_sliding_window": false,
99
+ "vocab_size": 151674
100
+ },
101
+ "max_dynamic_patch": 12,
102
+ "min_dynamic_patch": 1,
103
+ "model_type": "internvl_chat",
104
+ "pad2square": false,
105
+ "ps_version": "v2",
106
+ "select_layer": -1,
107
+ "template": "internvl2_5",
108
+ "tie_word_embeddings": false,
109
+ "torch_dtype": "bfloat16",
110
+ "transformers_version": null,
111
+ "use_backbone_lora": 0,
112
+ "use_cache": false,
113
+ "use_llm_lora": 0,
114
+ "use_thumbnail": true,
115
+ "vision_config": {
116
+ "_attn_implementation_autoset": true,
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": 0.0,
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
+ "task_specific_params": null,
186
+ "temperature": 1.0,
187
+ "tf_legacy_loss": false,
188
+ "tie_encoder_decoder": false,
189
+ "tie_word_embeddings": true,
190
+ "tokenizer_class": null,
191
+ "top_k": 50,
192
+ "top_p": 1.0,
193
+ "torch_dtype": "bfloat16",
194
+ "torchscript": false,
195
+ "transformers_version": "4.48.3",
196
+ "typical_p": 1.0,
197
+ "use_bfloat16": true,
198
+ "use_flash_attn": true
199
+ }
200
+ }