Hugging Face's logo

IDEA-CCNL
/
Ziya-Visual-14B-Chat

Visual Question Answering
Transformers
PyTorch
Chinese
English
blip-2
text2text-generation
ziya
fengshenbang
LVLM
visual question answering
Inference Endpoints
Model card Files Community
LinhIcey commited on
Commit
64cf752
•
1 Parent(s): 363f094

Upload 9 files

Browse files
Files changed (9) hide show
  1. added_tokens.json +3 -0
  2. config.json +252 -0
  3. pytorch_model-00001-of-00003.bin +3 -0
  4. pytorch_model-00002-of-00003.bin +3 -0
  5. pytorch_model-00003-of-00003.bin +3 -0
  6. pytorch_model.bin.index.json +0 -0
  7. special_tokens_map.json +34 -0
  8. tokenizer.model +3 -0
  9. tokenizer_config.json +41 -0
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<pad>": 39410
3
+ }
config.json ADDED
@@ -0,0 +1,252 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "/cognitive_comp/lujunyu/LLM/fengshen/workspace/instruct_ditto_ziya_qformer_all/hf_out_3_460000",
4
+ "architectures": [
5
+ "InstructDittoLMForConditionalGeneration"
6
+ ],
7
+ "assistant_name": "<bot>",
8
+ "human_name": "<human>",
9
+ "initializer_factor": 1.0,
10
+ "initializer_range": 0.02,
11
+ "model_type": "blip-2",
12
+ "num_query_tokens": 32,
13
+ "prompt_prefix": "",
14
+ "qformer_config": {
15
+ "_name_or_path": "",
16
+ "add_cross_attention": false,
17
+ "architectures": null,
18
+ "attention_probs_dropout_prob": 0.1,
19
+ "bad_words_ids": null,
20
+ "begin_suppress_tokens": null,
21
+ "bos_token_id": null,
22
+ "chunk_size_feed_forward": 0,
23
+ "classifier_dropout": null,
24
+ "cross_attention_frequency": 2,
25
+ "cross_attention_hidden_size": null,
26
+ "decoder_start_token_id": null,
27
+ "diversity_penalty": 0.0,
28
+ "do_sample": false,
29
+ "early_stopping": false,
30
+ "encoder_hidden_size": 1408,
31
+ "encoder_no_repeat_ngram_size": 0,
32
+ "eos_token_id": null,
33
+ "exponential_decay_length_penalty": null,
34
+ "finetuning_task": null,
35
+ "forced_bos_token_id": null,
36
+ "forced_eos_token_id": null,
37
+ "hidden_act": "gelu",
38
+ "hidden_dropout_prob": 0.1,
39
+ "hidden_size": 768,
40
+ "id2label": {
41
+ "0": "LABEL_0",
42
+ "1": "LABEL_1"
43
+ },
44
+ "initializer_range": 0.02,
45
+ "intermediate_size": 3072,
46
+ "is_decoder": false,
47
+ "is_encoder_decoder": false,
48
+ "label2id": {
49
+ "LABEL_0": 0,
50
+ "LABEL_1": 1
51
+ },
52
+ "layer_norm_eps": 1e-12,
53
+ "length_penalty": 1.0,
54
+ "max_length": 20,
55
+ "max_position_embeddings": 512,
56
+ "min_length": 0,
57
+ "model_type": "blip_2_qformer",
58
+ "no_repeat_ngram_size": 0,
59
+ "num_attention_heads": 12,
60
+ "num_beam_groups": 1,
61
+ "num_beams": 1,
62
+ "num_hidden_layers": 12,
63
+ "num_return_sequences": 1,
64
+ "output_attentions": false,
65
+ "output_hidden_states": false,
66
+ "output_scores": false,
67
+ "pad_token_id": 0,
68
+ "position_embedding_type": "absolute",
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
+ "sep_token_id": null,
77
+ "suppress_tokens": null,
78
+ "task_specific_params": null,
79
+ "temperature": 1.0,
80
+ "tf_legacy_loss": false,
81
+ "tie_encoder_decoder": false,
82
+ "tie_word_embeddings": true,
83
+ "tokenizer_class": null,
84
+ "top_k": 50,
85
+ "top_p": 1.0,
86
+ "torch_dtype": null,
87
+ "torchscript": false,
88
+ "transformers_version": "4.28.1",
89
+ "typical_p": 1.0,
90
+ "use_bfloat16": false,
91
+ "vocab_size": 44701
92
+ },
93
+ "text_config": {
94
+ "_name_or_path": "",
95
+ "add_cross_attention": false,
96
+ "architectures": [
97
+ "LlamaForCausalLM"
98
+ ],
99
+ "bad_words_ids": null,
100
+ "begin_suppress_tokens": null,
101
+ "bos_token_id": 1,
102
+ "chunk_size_feed_forward": 0,
103
+ "cross_attention_hidden_size": null,
104
+ "decoder_start_token_id": null,
105
+ "diversity_penalty": 0.0,
106
+ "do_sample": false,
107
+ "early_stopping": false,
108
+ "encoder_no_repeat_ngram_size": 0,
109
+ "eos_token_id": 2,
110
+ "exponential_decay_length_penalty": null,
111
+ "finetuning_task": null,
112
+ "forced_bos_token_id": null,
113
+ "forced_eos_token_id": null,
114
+ "hidden_act": "silu",
115
+ "hidden_size": 5120,
116
+ "id2label": {
117
+ "0": "LABEL_0",
118
+ "1": "LABEL_1"
119
+ },
120
+ "initializer_range": 0.02,
121
+ "intermediate_size": 13824,
122
+ "is_decoder": false,
123
+ "is_encoder_decoder": false,
124
+ "label2id": {
125
+ "LABEL_0": 0,
126
+ "LABEL_1": 1
127
+ },
128
+ "length_penalty": 1.0,
129
+ "max_length": 20,
130
+ "max_position_embeddings": 2048,
131
+ "min_length": 0,
132
+ "model_type": "llama",
133
+ "no_repeat_ngram_size": 0,
134
+ "num_attention_heads": 40,
135
+ "num_beam_groups": 1,
136
+ "num_beams": 1,
137
+ "num_hidden_layers": 40,
138
+ "num_return_sequences": 1,
139
+ "output_attentions": false,
140
+ "output_hidden_states": false,
141
+ "output_scores": false,
142
+ "pad_token_id": 0,
143
+ "prefix": null,
144
+ "problem_type": null,
145
+ "pruned_heads": {},
146
+ "remove_invalid_values": false,
147
+ "repetition_penalty": 1.0,
148
+ "return_dict": true,
149
+ "return_dict_in_generate": false,
150
+ "rms_norm_eps": 1e-06,
151
+ "sep_token_id": null,
152
+ "suppress_tokens": null,
153
+ "task_specific_params": null,
154
+ "temperature": 1.0,
155
+ "tf_legacy_loss": false,
156
+ "tie_encoder_decoder": false,
157
+ "tie_word_embeddings": false,
158
+ "tokenizer_class": null,
159
+ "top_k": 50,
160
+ "top_p": 1.0,
161
+ "torch_dtype": "float32",
162
+ "torchscript": false,
163
+ "transformers_version": "4.28.1",
164
+ "typical_p": 1.0,
165
+ "use_bfloat16": false,
166
+ "use_cache": true,
167
+ "vocab_size": 39424
168
+ },
169
+ "tie_word_embeddings": false,
170
+ "torch_dtype": "float16",
171
+ "transformers_version": null,
172
+ "use_decoder_only_language_model": true,
173
+ "vision_config": {
174
+ "_name_or_path": "",
175
+ "add_cross_attention": false,
176
+ "architectures": null,
177
+ "attention_dropout": 0.0,
178
+ "bad_words_ids": null,
179
+ "begin_suppress_tokens": null,
180
+ "bos_token_id": null,
181
+ "chunk_size_feed_forward": 0,
182
+ "cross_attention_hidden_size": null,
183
+ "decoder_start_token_id": null,
184
+ "diversity_penalty": 0.0,
185
+ "do_sample": false,
186
+ "dropout": 0.0,
187
+ "early_stopping": false,
188
+ "encoder_no_repeat_ngram_size": 0,
189
+ "eos_token_id": null,
190
+ "exponential_decay_length_penalty": null,
191
+ "finetuning_task": null,
192
+ "forced_bos_token_id": null,
193
+ "forced_eos_token_id": null,
194
+ "hidden_act": "gelu",
195
+ "hidden_size": 1408,
196
+ "id2label": {
197
+ "0": "LABEL_0",
198
+ "1": "LABEL_1"
199
+ },
200
+ "image_size": 224,
201
+ "initializer_factor": 1.0,
202
+ "initializer_range": 1e-10,
203
+ "intermediate_size": 6144,
204
+ "is_decoder": false,
205
+ "is_encoder_decoder": false,
206
+ "label2id": {
207
+ "LABEL_0": 0,
208
+ "LABEL_1": 1
209
+ },
210
+ "layer_norm_eps": 1e-05,
211
+ "length_penalty": 1.0,
212
+ "max_length": 20,
213
+ "min_length": 0,
214
+ "model_type": "blip_2_vision_model",
215
+ "no_repeat_ngram_size": 0,
216
+ "num_attention_heads": 16,
217
+ "num_beam_groups": 1,
218
+ "num_beams": 1,
219
+ "num_channels": 3,
220
+ "num_hidden_layers": 39,
221
+ "num_return_sequences": 1,
222
+ "output_attentions": false,
223
+ "output_hidden_states": false,
224
+ "output_scores": false,
225
+ "pad_token_id": null,
226
+ "patch_size": 14,
227
+ "prefix": null,
228
+ "problem_type": null,
229
+ "projection_dim": 512,
230
+ "pruned_heads": {},
231
+ "qkv_bias": true,
232
+ "remove_invalid_values": false,
233
+ "repetition_penalty": 1.0,
234
+ "return_dict": true,
235
+ "return_dict_in_generate": false,
236
+ "sep_token_id": null,
237
+ "suppress_tokens": null,
238
+ "task_specific_params": null,
239
+ "temperature": 1.0,
240
+ "tf_legacy_loss": false,
241
+ "tie_encoder_decoder": false,
242
+ "tie_word_embeddings": true,
243
+ "tokenizer_class": null,
244
+ "top_k": 50,
245
+ "top_p": 1.0,
246
+ "torch_dtype": null,
247
+ "torchscript": false,
248
+ "transformers_version": "4.28.1",
249
+ "typical_p": 1.0,
250
+ "use_bfloat16": false
251
+ }
252
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1c6583e6aab88d4c5e99d3c1498b03a94e5324e17c192e6cffa36b232f1c33e
3
+ size 9965101903
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f07e34af7e52042867a886280ab86d87f614bea9fcf3934dad54d393031c595
3
+ size 9993313745
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:969cff895247dfa786c775c5a86fbde0f987296358fa9d9a3b64049938c1d501
3
+ size 8598646951
pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<human>",
4
+ "<bot>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<s>",
8
+ "lstrip": false,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "</s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<pad>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:147fa8ef9267d7760a39e07a15eeadb64ce6560a74fa92f4e69cf206307e876c
3
+ size 588649
tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "model_max_length": 1000000000000000019884624838656,
22
+ "pad_token": {
23
+ "__type": "AddedToken",
24
+ "content": "<pad>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "sp_model_kwargs": {},
31
+ "tokenizer_class": "LlamaTokenizer",
32
+ "unk_token": {
33
+ "__type": "AddedToken",
34
+ "content": "<unk>",
35
+ "lstrip": false,
36
+ "normalized": true,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ },
40
+ "use_fast": false
41
+ }