khang119966 commited on
Commit
2832410
·
verified ·
1 Parent(s): da02d00

Upload ColInternVL2

Browse files
Files changed (3) hide show
  1. config.json +196 -0
  2. generation_config.json +9 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,196 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "4b1419d857c09c5b38e1c06ef9ebf64ddd221a79",
3
+ "_name_or_path": "5CD-AI/Vintern-1B-v3_5",
4
+ "architectures": [
5
+ "ColInternVL2"
6
+ ],
7
+ "auto_map": {
8
+ "AutoConfig": "5CD-AI/Vintern-1B-v3_5--configuration_internvl_chat.InternVLChatConfig",
9
+ "AutoModel": "5CD-AI/Vintern-1B-v3_5--modeling_internvl_chat.InternVLChatModel",
10
+ "AutoModelForCausalLM": "5CD-AI/Vintern-1B-v3_5--modeling_internvl_chat.InternVLChatModel"
11
+ },
12
+ "downsample_ratio": 0.5,
13
+ "dynamic_image_size": true,
14
+ "force_image_size": 448,
15
+ "llm_config": {
16
+ "_attn_implementation_autoset": true,
17
+ "_name_or_path": "Qwen/Qwen2.5-0.5B-Instruct",
18
+ "add_cross_attention": false,
19
+ "architectures": [
20
+ "Qwen2ForCausalLM"
21
+ ],
22
+ "attention_dropout": 0.0,
23
+ "bad_words_ids": null,
24
+ "begin_suppress_tokens": null,
25
+ "bos_token_id": 151643,
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": 151645,
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": 896,
40
+ "id2label": {
41
+ "0": "LABEL_0",
42
+ "1": "LABEL_1"
43
+ },
44
+ "initializer_range": 0.02,
45
+ "intermediate_size": 4864,
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
+ "max_window_layers": 21,
56
+ "min_length": 0,
57
+ "model_type": "qwen2",
58
+ "no_repeat_ngram_size": 0,
59
+ "num_attention_heads": 14,
60
+ "num_beam_groups": 1,
61
+ "num_beams": 1,
62
+ "num_hidden_layers": 24,
63
+ "num_key_value_heads": 2,
64
+ "num_return_sequences": 1,
65
+ "output_attentions": false,
66
+ "output_hidden_states": false,
67
+ "output_scores": false,
68
+ "pad_token_id": null,
69
+ "prefix": null,
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-06,
77
+ "rope_scaling": null,
78
+ "rope_theta": 1000000.0,
79
+ "sep_token_id": null,
80
+ "sliding_window": null,
81
+ "suppress_tokens": null,
82
+ "task_specific_params": null,
83
+ "temperature": 1.0,
84
+ "tf_legacy_loss": false,
85
+ "tie_encoder_decoder": false,
86
+ "tie_word_embeddings": false,
87
+ "tokenizer_class": null,
88
+ "top_k": 50,
89
+ "top_p": 1.0,
90
+ "torch_dtype": "bfloat16",
91
+ "torchscript": false,
92
+ "transformers_version": "4.48.2",
93
+ "typical_p": 1.0,
94
+ "use_bfloat16": true,
95
+ "use_cache": false,
96
+ "use_sliding_window": false,
97
+ "vocab_size": 151674
98
+ },
99
+ "max_dynamic_patch": 4,
100
+ "min_dynamic_patch": 1,
101
+ "model_type": "internvl_chat",
102
+ "pad2square": false,
103
+ "ps_version": "v2",
104
+ "select_layer": -1,
105
+ "template": "Hermes-2",
106
+ "torch_dtype": "bfloat16",
107
+ "transformers_version": null,
108
+ "use_backbone_lora": 0,
109
+ "use_llm_lora": 0,
110
+ "use_thumbnail": true,
111
+ "vision_config": {
112
+ "_attn_implementation_autoset": true,
113
+ "_name_or_path": "",
114
+ "add_cross_attention": false,
115
+ "architectures": [
116
+ "InternVisionModel"
117
+ ],
118
+ "attention_dropout": 0.0,
119
+ "bad_words_ids": null,
120
+ "begin_suppress_tokens": null,
121
+ "bos_token_id": null,
122
+ "chunk_size_feed_forward": 0,
123
+ "cross_attention_hidden_size": null,
124
+ "decoder_start_token_id": null,
125
+ "diversity_penalty": 0.0,
126
+ "do_sample": false,
127
+ "drop_path_rate": 0.0,
128
+ "dropout": 0.0,
129
+ "early_stopping": false,
130
+ "encoder_no_repeat_ngram_size": 0,
131
+ "eos_token_id": null,
132
+ "exponential_decay_length_penalty": null,
133
+ "finetuning_task": null,
134
+ "forced_bos_token_id": null,
135
+ "forced_eos_token_id": null,
136
+ "hidden_act": "gelu",
137
+ "hidden_size": 1024,
138
+ "id2label": {
139
+ "0": "LABEL_0",
140
+ "1": "LABEL_1"
141
+ },
142
+ "image_size": 448,
143
+ "initializer_factor": 1.0,
144
+ "initializer_range": 0.02,
145
+ "intermediate_size": 4096,
146
+ "is_decoder": false,
147
+ "is_encoder_decoder": false,
148
+ "label2id": {
149
+ "LABEL_0": 0,
150
+ "LABEL_1": 1
151
+ },
152
+ "layer_norm_eps": 1e-06,
153
+ "length_penalty": 1.0,
154
+ "max_length": 20,
155
+ "min_length": 0,
156
+ "model_type": "intern_vit_6b",
157
+ "no_repeat_ngram_size": 0,
158
+ "norm_type": "layer_norm",
159
+ "num_attention_heads": 16,
160
+ "num_beam_groups": 1,
161
+ "num_beams": 1,
162
+ "num_channels": 3,
163
+ "num_hidden_layers": 24,
164
+ "num_return_sequences": 1,
165
+ "output_attentions": false,
166
+ "output_hidden_states": false,
167
+ "output_scores": false,
168
+ "pad_token_id": null,
169
+ "patch_size": 14,
170
+ "prefix": null,
171
+ "problem_type": null,
172
+ "pruned_heads": {},
173
+ "qk_normalization": false,
174
+ "qkv_bias": true,
175
+ "remove_invalid_values": false,
176
+ "repetition_penalty": 1.0,
177
+ "return_dict": true,
178
+ "return_dict_in_generate": false,
179
+ "sep_token_id": null,
180
+ "suppress_tokens": null,
181
+ "task_specific_params": null,
182
+ "temperature": 1.0,
183
+ "tf_legacy_loss": false,
184
+ "tie_encoder_decoder": false,
185
+ "tie_word_embeddings": true,
186
+ "tokenizer_class": null,
187
+ "top_k": 50,
188
+ "top_p": 1.0,
189
+ "torch_dtype": "bfloat16",
190
+ "torchscript": false,
191
+ "transformers_version": "4.48.2",
192
+ "typical_p": 1.0,
193
+ "use_bfloat16": true,
194
+ "use_flash_attn": false
195
+ }
196
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": [
4
+ 151644,
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "transformers_version": "4.48.2"
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e9fe630e52588c84dd6c55f9c406f8687ebf7852646406e05d64f5edc18b04d
3
+ size 1876693280