aaronb commited on
Commit
b621d01
1 Parent(s): 1d63199

Upload 6 files

Browse files
husky-7b-delta-v0_01/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "</img>": 32001,
3
+ "<ImageContent>": 32002,
4
+ "<img>": 32000
5
+ }
husky-7b-delta-v0_01/config.json ADDED
@@ -0,0 +1,255 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "/mnt/petrelfs/share_data/zhangqinglong/Husky/work_dirs/husky-7b-v0_01",
4
+ "architectures": [
5
+ "Blip2LlaMAForConditionalGeneration"
6
+ ],
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_size": 4096,
10
+ "initializer_factor": 1.0,
11
+ "initializer_range": 0.02,
12
+ "model_type": "blip-2",
13
+ "num_query_tokens": 32,
14
+ "pad_token_id": 0,
15
+ "qformer_config": {
16
+ "_name_or_path": "",
17
+ "add_cross_attention": false,
18
+ "architectures": null,
19
+ "attention_probs_dropout_prob": 0.1,
20
+ "bad_words_ids": null,
21
+ "begin_suppress_tokens": null,
22
+ "bos_token_id": null,
23
+ "chunk_size_feed_forward": 0,
24
+ "classifier_dropout": null,
25
+ "cross_attention_frequency": 2,
26
+ "cross_attention_hidden_size": null,
27
+ "decoder_start_token_id": null,
28
+ "diversity_penalty": 0.0,
29
+ "do_sample": false,
30
+ "early_stopping": false,
31
+ "encoder_hidden_size": 1408,
32
+ "encoder_no_repeat_ngram_size": 0,
33
+ "eos_token_id": null,
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": "gelu",
39
+ "hidden_dropout_prob": 0.1,
40
+ "hidden_size": 768,
41
+ "id2label": {
42
+ "0": "LABEL_0",
43
+ "1": "LABEL_1"
44
+ },
45
+ "initializer_range": 0.02,
46
+ "intermediate_size": 3072,
47
+ "is_decoder": false,
48
+ "is_encoder_decoder": false,
49
+ "label2id": {
50
+ "LABEL_0": 0,
51
+ "LABEL_1": 1
52
+ },
53
+ "layer_norm_eps": 1e-12,
54
+ "length_penalty": 1.0,
55
+ "max_length": 20,
56
+ "max_position_embeddings": 512,
57
+ "min_length": 0,
58
+ "model_type": "blip_2_qformer",
59
+ "no_repeat_ngram_size": 0,
60
+ "num_attention_heads": 12,
61
+ "num_beam_groups": 1,
62
+ "num_beams": 1,
63
+ "num_hidden_layers": 12,
64
+ "num_return_sequences": 1,
65
+ "output_attentions": false,
66
+ "output_hidden_states": false,
67
+ "output_scores": false,
68
+ "pad_token_id": 0,
69
+ "position_embedding_type": "absolute",
70
+ "prefix": null,
71
+ "problem_type": null,
72
+ "pruned_heads": {},
73
+ "remove_invalid_values": false,
74
+ "repetition_penalty": 1.0,
75
+ "return_dict": true,
76
+ "return_dict_in_generate": false,
77
+ "sep_token_id": null,
78
+ "suppress_tokens": null,
79
+ "task_specific_params": null,
80
+ "temperature": 1.0,
81
+ "tf_legacy_loss": false,
82
+ "tie_encoder_decoder": false,
83
+ "tie_word_embeddings": true,
84
+ "tokenizer_class": null,
85
+ "top_k": 50,
86
+ "top_p": 1.0,
87
+ "torch_dtype": null,
88
+ "torchscript": false,
89
+ "transformers_version": "4.28.1",
90
+ "typical_p": 1.0,
91
+ "use_bfloat16": false,
92
+ "vocab_size": 30522
93
+ },
94
+ "text_config": {
95
+ "_name_or_path": "",
96
+ "add_cross_attention": false,
97
+ "architectures": [
98
+ "LlamaForCausalLM"
99
+ ],
100
+ "bad_words_ids": null,
101
+ "begin_suppress_tokens": null,
102
+ "bos_token_id": 1,
103
+ "chunk_size_feed_forward": 0,
104
+ "cross_attention_hidden_size": null,
105
+ "decoder_start_token_id": null,
106
+ "diversity_penalty": 0.0,
107
+ "do_sample": false,
108
+ "early_stopping": false,
109
+ "encoder_no_repeat_ngram_size": 0,
110
+ "eos_token_id": 2,
111
+ "exponential_decay_length_penalty": null,
112
+ "finetuning_task": null,
113
+ "forced_bos_token_id": null,
114
+ "forced_eos_token_id": null,
115
+ "hidden_act": "silu",
116
+ "hidden_size": 4096,
117
+ "id2label": {
118
+ "0": "LABEL_0",
119
+ "1": "LABEL_1"
120
+ },
121
+ "initializer_range": 0.02,
122
+ "intermediate_size": 11008,
123
+ "is_decoder": false,
124
+ "is_encoder_decoder": false,
125
+ "label2id": {
126
+ "LABEL_0": 0,
127
+ "LABEL_1": 1
128
+ },
129
+ "length_penalty": 1.0,
130
+ "max_length": 20,
131
+ "max_position_embeddings": 2048,
132
+ "max_sequence_length": 2048,
133
+ "min_length": 0,
134
+ "model_type": "llama",
135
+ "no_repeat_ngram_size": 0,
136
+ "num_attention_heads": 32,
137
+ "num_beam_groups": 1,
138
+ "num_beams": 1,
139
+ "num_hidden_layers": 32,
140
+ "num_return_sequences": 1,
141
+ "output_attentions": false,
142
+ "output_hidden_states": false,
143
+ "output_scores": false,
144
+ "pad_token_id": 0,
145
+ "prefix": null,
146
+ "problem_type": null,
147
+ "pruned_heads": {},
148
+ "remove_invalid_values": false,
149
+ "repetition_penalty": 1.0,
150
+ "return_dict": true,
151
+ "return_dict_in_generate": false,
152
+ "rms_norm_eps": 1e-06,
153
+ "sep_token_id": null,
154
+ "suppress_tokens": null,
155
+ "task_specific_params": null,
156
+ "temperature": 1.0,
157
+ "tf_legacy_loss": false,
158
+ "tie_encoder_decoder": false,
159
+ "tie_word_embeddings": false,
160
+ "tokenizer_class": null,
161
+ "top_k": 50,
162
+ "top_p": 1.0,
163
+ "torch_dtype": "float16",
164
+ "torchscript": false,
165
+ "transformers_version": "4.28.1",
166
+ "typical_p": 1.0,
167
+ "use_bfloat16": false,
168
+ "use_cache": true,
169
+ "vocab_size": 32003
170
+ },
171
+ "tie_word_embeddings": false,
172
+ "torch_dtype": "float16",
173
+ "transformers_version": null,
174
+ "use_cache": false,
175
+ "use_decoder_only_language_model": true,
176
+ "vision_config": {
177
+ "_name_or_path": "",
178
+ "add_cross_attention": false,
179
+ "architectures": null,
180
+ "attention_dropout": 0.0,
181
+ "bad_words_ids": null,
182
+ "begin_suppress_tokens": null,
183
+ "bos_token_id": null,
184
+ "chunk_size_feed_forward": 0,
185
+ "cross_attention_hidden_size": null,
186
+ "decoder_start_token_id": null,
187
+ "diversity_penalty": 0.0,
188
+ "do_sample": false,
189
+ "dropout": 0.0,
190
+ "early_stopping": false,
191
+ "encoder_no_repeat_ngram_size": 0,
192
+ "eos_token_id": null,
193
+ "exponential_decay_length_penalty": null,
194
+ "finetuning_task": null,
195
+ "forced_bos_token_id": null,
196
+ "forced_eos_token_id": null,
197
+ "hidden_act": "gelu",
198
+ "hidden_size": 1408,
199
+ "id2label": {
200
+ "0": "LABEL_0",
201
+ "1": "LABEL_1"
202
+ },
203
+ "image_size": 224,
204
+ "initializer_factor": 1.0,
205
+ "initializer_range": 1e-10,
206
+ "intermediate_size": 6144,
207
+ "is_decoder": false,
208
+ "is_encoder_decoder": false,
209
+ "label2id": {
210
+ "LABEL_0": 0,
211
+ "LABEL_1": 1
212
+ },
213
+ "layer_norm_eps": 1e-05,
214
+ "length_penalty": 1.0,
215
+ "max_length": 20,
216
+ "min_length": 0,
217
+ "model_type": "blip_2_vision_model",
218
+ "no_repeat_ngram_size": 0,
219
+ "num_attention_heads": 16,
220
+ "num_beam_groups": 1,
221
+ "num_beams": 1,
222
+ "num_channels": 3,
223
+ "num_hidden_layers": 39,
224
+ "num_return_sequences": 1,
225
+ "output_attentions": false,
226
+ "output_hidden_states": false,
227
+ "output_scores": false,
228
+ "pad_token_id": null,
229
+ "patch_size": 14,
230
+ "prefix": null,
231
+ "problem_type": null,
232
+ "projection_dim": 512,
233
+ "pruned_heads": {},
234
+ "qkv_bias": true,
235
+ "remove_invalid_values": false,
236
+ "repetition_penalty": 1.0,
237
+ "return_dict": true,
238
+ "return_dict_in_generate": false,
239
+ "sep_token_id": null,
240
+ "suppress_tokens": null,
241
+ "task_specific_params": null,
242
+ "temperature": 1.0,
243
+ "tf_legacy_loss": false,
244
+ "tie_encoder_decoder": false,
245
+ "tie_word_embeddings": true,
246
+ "tokenizer_class": null,
247
+ "top_k": 50,
248
+ "top_p": 1.0,
249
+ "torch_dtype": null,
250
+ "torchscript": false,
251
+ "transformers_version": "4.28.1",
252
+ "typical_p": 1.0,
253
+ "use_bfloat16": false
254
+ }
255
+ }
husky-7b-delta-v0_01/pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff
 
husky-7b-delta-v0_01/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
husky-7b-delta-v0_01/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
husky-7b-delta-v0_01/tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": null,
23
+ "sp_model_kwargs": {},
24
+ "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }