Hugging Face's logo

Mediocreatmybest
/
blip2-flan-t5-xxl_8bit

Visual Question Answering
Transformers
PyTorch
blip-2
Inference Endpoints
8-bit precision
Model card Files Community
1
Mediocreatmybest commited on
Commit
a5b54b4
•
1 Parent(s): 647f151

Upload Blip2ForConditionalGeneration

Browse files
Files changed (5) hide show
  1. config.json +268 -0
  2. pytorch_model-00001-of-00003.bin +3 -0
  3. pytorch_model-00002-of-00003.bin +3 -0
  4. pytorch_model-00003-of-00003.bin +3 -0
  5. pytorch_model.bin.index.json +0 -0
config.json ADDED
@@ -0,0 +1,268 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "7bf1f0bfa6d7ae96cec030810538259f7e5e054e",
3
+ "_name_or_path": "Salesforce/blip2-flan-t5-xxl",
4
+ "architectures": [
5
+ "Blip2ForConditionalGeneration"
6
+ ],
7
+ "initializer_factor": 1.0,
8
+ "initializer_range": 0.02,
9
+ "is_encoder_decoder": true,
10
+ "model_type": "blip-2",
11
+ "num_query_tokens": 32,
12
+ "qformer_config": {
13
+ "_name_or_path": "",
14
+ "add_cross_attention": false,
15
+ "architectures": null,
16
+ "attention_probs_dropout_prob": 0.1,
17
+ "bad_words_ids": null,
18
+ "begin_suppress_tokens": null,
19
+ "bos_token_id": null,
20
+ "chunk_size_feed_forward": 0,
21
+ "classifier_dropout": null,
22
+ "cross_attention_frequency": 2,
23
+ "cross_attention_hidden_size": null,
24
+ "decoder_start_token_id": null,
25
+ "diversity_penalty": 0.0,
26
+ "do_sample": false,
27
+ "early_stopping": false,
28
+ "encoder_hidden_size": 1408,
29
+ "encoder_no_repeat_ngram_size": 0,
30
+ "eos_token_id": null,
31
+ "exponential_decay_length_penalty": null,
32
+ "finetuning_task": null,
33
+ "forced_bos_token_id": null,
34
+ "forced_eos_token_id": null,
35
+ "hidden_act": "gelu",
36
+ "hidden_dropout_prob": 0.1,
37
+ "hidden_size": 768,
38
+ "id2label": {
39
+ "0": "LABEL_0",
40
+ "1": "LABEL_1"
41
+ },
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 3072,
44
+ "is_decoder": false,
45
+ "is_encoder_decoder": false,
46
+ "label2id": {
47
+ "LABEL_0": 0,
48
+ "LABEL_1": 1
49
+ },
50
+ "layer_norm_eps": 1e-12,
51
+ "length_penalty": 1.0,
52
+ "max_length": 20,
53
+ "max_position_embeddings": 512,
54
+ "min_length": 0,
55
+ "model_type": "blip_2_qformer",
56
+ "no_repeat_ngram_size": 0,
57
+ "num_attention_heads": 12,
58
+ "num_beam_groups": 1,
59
+ "num_beams": 1,
60
+ "num_hidden_layers": 12,
61
+ "num_return_sequences": 1,
62
+ "output_attentions": false,
63
+ "output_hidden_states": false,
64
+ "output_scores": false,
65
+ "pad_token_id": 0,
66
+ "position_embedding_type": "absolute",
67
+ "prefix": null,
68
+ "problem_type": null,
69
+ "pruned_heads": {},
70
+ "remove_invalid_values": false,
71
+ "repetition_penalty": 1.0,
72
+ "return_dict": true,
73
+ "return_dict_in_generate": false,
74
+ "sep_token_id": null,
75
+ "suppress_tokens": null,
76
+ "task_specific_params": null,
77
+ "temperature": 1.0,
78
+ "tf_legacy_loss": false,
79
+ "tie_encoder_decoder": false,
80
+ "tie_word_embeddings": true,
81
+ "tokenizer_class": null,
82
+ "top_k": 50,
83
+ "top_p": 1.0,
84
+ "torch_dtype": null,
85
+ "torchscript": false,
86
+ "transformers_version": "4.30.2",
87
+ "typical_p": 1.0,
88
+ "use_bfloat16": false,
89
+ "vocab_size": 30522
90
+ },
91
+ "quantization_config": {
92
+ "bnb_4bit_compute_dtype": "float32",
93
+ "bnb_4bit_quant_type": "fp4",
94
+ "bnb_4bit_use_double_quant": false,
95
+ "llm_int8_enable_fp32_cpu_offload": false,
96
+ "llm_int8_has_fp16_weight": false,
97
+ "llm_int8_skip_modules": null,
98
+ "llm_int8_threshold": 6.0,
99
+ "load_in_4bit": false,
100
+ "load_in_8bit": true
101
+ },
102
+ "text_config": {
103
+ "_name_or_path": "",
104
+ "add_cross_attention": false,
105
+ "architectures": [
106
+ "T5ForConditionalGeneration"
107
+ ],
108
+ "bad_words_ids": null,
109
+ "begin_suppress_tokens": null,
110
+ "bos_token_id": 1,
111
+ "chunk_size_feed_forward": 0,
112
+ "cross_attention_hidden_size": null,
113
+ "d_ff": 10240,
114
+ "d_kv": 64,
115
+ "d_model": 4096,
116
+ "decoder_start_token_id": 0,
117
+ "dense_act_fn": "gelu",
118
+ "diversity_penalty": 0.0,
119
+ "do_sample": false,
120
+ "dropout_rate": 0.1,
121
+ "early_stopping": false,
122
+ "encoder_no_repeat_ngram_size": 0,
123
+ "eos_token_id": 1,
124
+ "exponential_decay_length_penalty": null,
125
+ "feed_forward_proj": "gated-gelu",
126
+ "finetuning_task": null,
127
+ "forced_bos_token_id": null,
128
+ "forced_eos_token_id": null,
129
+ "id2label": {
130
+ "0": "LABEL_0",
131
+ "1": "LABEL_1"
132
+ },
133
+ "initializer_factor": 1.0,
134
+ "is_decoder": false,
135
+ "is_encoder_decoder": true,
136
+ "is_gated_act": true,
137
+ "label2id": {
138
+ "LABEL_0": 0,
139
+ "LABEL_1": 1
140
+ },
141
+ "layer_norm_epsilon": 1e-06,
142
+ "length_penalty": 1.0,
143
+ "max_length": 20,
144
+ "min_length": 0,
145
+ "model_type": "t5",
146
+ "no_repeat_ngram_size": 0,
147
+ "num_beam_groups": 1,
148
+ "num_beams": 1,
149
+ "num_decoder_layers": 24,
150
+ "num_heads": 64,
151
+ "num_layers": 24,
152
+ "num_return_sequences": 1,
153
+ "output_attentions": false,
154
+ "output_hidden_states": false,
155
+ "output_past": true,
156
+ "output_scores": false,
157
+ "pad_token_id": 0,
158
+ "prefix": null,
159
+ "problem_type": null,
160
+ "pruned_heads": {},
161
+ "relative_attention_max_distance": 128,
162
+ "relative_attention_num_buckets": 32,
163
+ "remove_invalid_values": false,
164
+ "repetition_penalty": 1.0,
165
+ "return_dict": true,
166
+ "return_dict_in_generate": false,
167
+ "sep_token_id": null,
168
+ "suppress_tokens": null,
169
+ "task_specific_params": null,
170
+ "temperature": 1.0,
171
+ "tf_legacy_loss": false,
172
+ "tie_encoder_decoder": false,
173
+ "tie_word_embeddings": false,
174
+ "tokenizer_class": null,
175
+ "top_k": 50,
176
+ "top_p": 1.0,
177
+ "torch_dtype": "float32",
178
+ "torchscript": false,
179
+ "transformers_version": "4.30.2",
180
+ "typical_p": 1.0,
181
+ "use_bfloat16": false,
182
+ "use_cache": true,
183
+ "vocab_size": 32128
184
+ },
185
+ "tie_word_embeddings": false,
186
+ "torch_dtype": "float16",
187
+ "transformers_version": null,
188
+ "use_decoder_only_language_model": false,
189
+ "vision_config": {
190
+ "_name_or_path": "",
191
+ "add_cross_attention": false,
192
+ "architectures": null,
193
+ "attention_dropout": 0.0,
194
+ "bad_words_ids": null,
195
+ "begin_suppress_tokens": null,
196
+ "bos_token_id": null,
197
+ "chunk_size_feed_forward": 0,
198
+ "cross_attention_hidden_size": null,
199
+ "decoder_start_token_id": null,
200
+ "diversity_penalty": 0.0,
201
+ "do_sample": false,
202
+ "dropout": 0.0,
203
+ "early_stopping": false,
204
+ "encoder_no_repeat_ngram_size": 0,
205
+ "eos_token_id": null,
206
+ "exponential_decay_length_penalty": null,
207
+ "finetuning_task": null,
208
+ "forced_bos_token_id": null,
209
+ "forced_eos_token_id": null,
210
+ "hidden_act": "gelu",
211
+ "hidden_size": 1408,
212
+ "id2label": {
213
+ "0": "LABEL_0",
214
+ "1": "LABEL_1"
215
+ },
216
+ "image_size": 224,
217
+ "initializer_factor": 1.0,
218
+ "initializer_range": 1e-10,
219
+ "intermediate_size": 6144,
220
+ "is_decoder": false,
221
+ "is_encoder_decoder": false,
222
+ "label2id": {
223
+ "LABEL_0": 0,
224
+ "LABEL_1": 1
225
+ },
226
+ "layer_norm_eps": 1e-05,
227
+ "length_penalty": 1.0,
228
+ "max_length": 20,
229
+ "min_length": 0,
230
+ "model_type": "blip_2_vision_model",
231
+ "no_repeat_ngram_size": 0,
232
+ "num_attention_heads": 16,
233
+ "num_beam_groups": 1,
234
+ "num_beams": 1,
235
+ "num_channels": 3,
236
+ "num_hidden_layers": 39,
237
+ "num_return_sequences": 1,
238
+ "output_attentions": false,
239
+ "output_hidden_states": false,
240
+ "output_scores": false,
241
+ "pad_token_id": null,
242
+ "patch_size": 14,
243
+ "prefix": null,
244
+ "problem_type": null,
245
+ "projection_dim": 512,
246
+ "pruned_heads": {},
247
+ "qkv_bias": true,
248
+ "remove_invalid_values": false,
249
+ "repetition_penalty": 1.0,
250
+ "return_dict": true,
251
+ "return_dict_in_generate": false,
252
+ "sep_token_id": null,
253
+ "suppress_tokens": null,
254
+ "task_specific_params": null,
255
+ "temperature": 1.0,
256
+ "tf_legacy_loss": false,
257
+ "tie_encoder_decoder": false,
258
+ "tie_word_embeddings": true,
259
+ "tokenizer_class": null,
260
+ "top_k": 50,
261
+ "top_p": 1.0,
262
+ "torch_dtype": null,
263
+ "torchscript": false,
264
+ "transformers_version": "4.30.2",
265
+ "typical_p": 1.0,
266
+ "use_bfloat16": false
267
+ }
268
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed709bd38245385028be70071eead7489ef310a6045bef77a00fe6c2e6b783dd
3
+ size 9968489134
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcc68e5756c1ea541871842b1c52b2867a33b8b17a47248db3e121bdaa6d8c4b
3
+ size 9999699394
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49ec175f8cfadb3bdca90a997dd23035ef6c9faae3a7137f85a059d79e0c9661
3
+ size 8517997116
pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff