czczup commited on
Commit
95d74f8
1 Parent(s): 6caedeb

Update README.md

Browse files
Files changed (2) hide show
  1. README.md +1 -1
  2. config.json +0 -55
README.md CHANGED
@@ -291,7 +291,7 @@ print(response)
291
 
292
  ## License
293
 
294
- This project is released under the MIT License. This project uses the pre-trained Qwen2.5-3B-Instruct as a component, which is licensed under the Apache License 2.0.
295
 
296
  ## Citation
297
 
 
291
 
292
  ## License
293
 
294
+ This project is released under the MIT License. This project uses the pre-trained internlm2_5-20b-chat as a component, which is licensed under the Apache License 2.0.
295
 
296
  ## Citation
297
 
config.json CHANGED
@@ -117,91 +117,36 @@
117
  "select_layer": -1,
118
  "template": "internvl2_5",
119
  "torch_dtype": "float16",
120
- "transformers_version": null,
121
  "use_backbone_lora": 0,
122
  "use_llm_lora": 0,
123
  "use_thumbnail": true,
124
  "vision_config": {
125
- "_name_or_path": "",
126
- "add_cross_attention": false,
127
  "architectures": [
128
  "InternVisionModel"
129
  ],
130
  "attention_dropout": 0.0,
131
- "bad_words_ids": null,
132
- "begin_suppress_tokens": null,
133
- "bos_token_id": null,
134
- "chunk_size_feed_forward": 0,
135
- "cross_attention_hidden_size": null,
136
- "decoder_start_token_id": null,
137
- "diversity_penalty": 0.0,
138
- "do_sample": false,
139
  "drop_path_rate": 0.0,
140
  "dropout": 0.0,
141
- "early_stopping": false,
142
- "encoder_no_repeat_ngram_size": 0,
143
- "eos_token_id": null,
144
- "exponential_decay_length_penalty": null,
145
- "finetuning_task": null,
146
- "forced_bos_token_id": null,
147
- "forced_eos_token_id": null,
148
  "hidden_act": "gelu",
149
  "hidden_size": 3200,
150
- "id2label": {
151
- "0": "LABEL_0",
152
- "1": "LABEL_1"
153
- },
154
  "image_size": 448,
155
  "initializer_factor": 0.1,
156
  "initializer_range": 1e-10,
157
  "intermediate_size": 12800,
158
- "is_decoder": false,
159
- "is_encoder_decoder": false,
160
- "label2id": {
161
- "LABEL_0": 0,
162
- "LABEL_1": 1
163
- },
164
  "layer_norm_eps": 1e-06,
165
- "length_penalty": 1.0,
166
- "max_length": 20,
167
- "min_length": 0,
168
  "model_type": "intern_vit_6b",
169
- "no_repeat_ngram_size": 0,
170
  "norm_type": "rms_norm",
171
  "num_attention_heads": 25,
172
- "num_beam_groups": 1,
173
- "num_beams": 1,
174
  "num_channels": 3,
175
  "num_hidden_layers": 45,
176
- "num_return_sequences": 1,
177
  "output_attentions": false,
178
  "output_hidden_states": false,
179
- "output_scores": false,
180
- "pad_token_id": null,
181
  "patch_size": 14,
182
- "prefix": null,
183
- "problem_type": null,
184
- "pruned_heads": {},
185
  "qk_normalization": true,
186
  "qkv_bias": false,
187
- "remove_invalid_values": false,
188
- "repetition_penalty": 1.0,
189
  "return_dict": true,
190
- "return_dict_in_generate": false,
191
- "sep_token_id": null,
192
- "suppress_tokens": null,
193
- "task_specific_params": null,
194
- "temperature": 1.0,
195
- "tf_legacy_loss": false,
196
- "tie_encoder_decoder": false,
197
- "tie_word_embeddings": true,
198
- "tokenizer_class": null,
199
- "top_k": 50,
200
- "top_p": 1.0,
201
  "torch_dtype": "bfloat16",
202
- "torchscript": false,
203
  "transformers_version": "4.45.1",
204
- "typical_p": 1.0,
205
  "use_bfloat16": true,
206
  "use_flash_attn": true
207
  }
 
117
  "select_layer": -1,
118
  "template": "internvl2_5",
119
  "torch_dtype": "float16",
 
120
  "use_backbone_lora": 0,
121
  "use_llm_lora": 0,
122
  "use_thumbnail": true,
123
  "vision_config": {
 
 
124
  "architectures": [
125
  "InternVisionModel"
126
  ],
127
  "attention_dropout": 0.0,
 
 
 
 
 
 
 
 
128
  "drop_path_rate": 0.0,
129
  "dropout": 0.0,
 
 
 
 
 
 
 
130
  "hidden_act": "gelu",
131
  "hidden_size": 3200,
 
 
 
 
132
  "image_size": 448,
133
  "initializer_factor": 0.1,
134
  "initializer_range": 1e-10,
135
  "intermediate_size": 12800,
 
 
 
 
 
 
136
  "layer_norm_eps": 1e-06,
 
 
 
137
  "model_type": "intern_vit_6b",
 
138
  "norm_type": "rms_norm",
139
  "num_attention_heads": 25,
 
 
140
  "num_channels": 3,
141
  "num_hidden_layers": 45,
 
142
  "output_attentions": false,
143
  "output_hidden_states": false,
 
 
144
  "patch_size": 14,
 
 
 
145
  "qk_normalization": true,
146
  "qkv_bias": false,
 
 
147
  "return_dict": true,
 
 
 
 
 
 
 
 
 
 
 
148
  "torch_dtype": "bfloat16",
 
149
  "transformers_version": "4.45.1",
 
150
  "use_bfloat16": true,
151
  "use_flash_attn": true
152
  }