Upload model
Browse files- config.json +468 -28
- pytorch_model.bin +2 -2
config.json
CHANGED
@@ -8,14 +8,18 @@
|
|
8 |
"model_type": "clip",
|
9 |
"projection_dim": 512,
|
10 |
"text_config": {
|
11 |
-
"_name_or_path": "",
|
12 |
"add_cross_attention": false,
|
13 |
-
"architectures":
|
|
|
|
|
14 |
"attention_dropout": 0.0,
|
|
|
15 |
"bad_words_ids": null,
|
16 |
"begin_suppress_tokens": null,
|
17 |
"bos_token_id": 0,
|
18 |
"chunk_size_feed_forward": 0,
|
|
|
19 |
"cross_attention_hidden_size": null,
|
20 |
"decoder_start_token_id": null,
|
21 |
"diversity_penalty": 0.0,
|
@@ -28,7 +32,9 @@
|
|
28 |
"finetuning_task": null,
|
29 |
"forced_bos_token_id": null,
|
30 |
"forced_eos_token_id": null,
|
31 |
-
"
|
|
|
|
|
32 |
"hidden_size": 768,
|
33 |
"id2label": {
|
34 |
"0": "LABEL_0",
|
@@ -36,30 +42,30 @@
|
|
36 |
},
|
37 |
"initializer_factor": 1.0,
|
38 |
"initializer_range": 0.02,
|
39 |
-
"intermediate_size":
|
40 |
"is_decoder": false,
|
41 |
"is_encoder_decoder": false,
|
42 |
"label2id": {
|
43 |
"LABEL_0": 0,
|
44 |
"LABEL_1": 1
|
45 |
},
|
46 |
-
"layer_norm_eps": 1e-
|
47 |
"length_penalty": 1.0,
|
48 |
"max_length": 20,
|
49 |
-
"max_position_embeddings":
|
50 |
"min_length": 0,
|
51 |
"model_type": "clip_text_model",
|
52 |
"no_repeat_ngram_size": 0,
|
53 |
-
"num_attention_heads":
|
54 |
"num_beam_groups": 1,
|
55 |
"num_beams": 1,
|
56 |
-
"num_hidden_layers":
|
57 |
"num_return_sequences": 1,
|
58 |
"output_attentions": false,
|
59 |
"output_hidden_states": false,
|
60 |
"output_scores": false,
|
61 |
"pad_token_id": 1,
|
62 |
-
"
|
63 |
"prefix": null,
|
64 |
"problem_type": null,
|
65 |
"pruned_heads": {},
|
@@ -77,26 +83,105 @@
|
|
77 |
"tokenizer_class": null,
|
78 |
"top_k": 50,
|
79 |
"top_p": 1.0,
|
80 |
-
"torch_dtype":
|
81 |
"torchscript": false,
|
82 |
"transformers_version": "4.24.0",
|
|
|
83 |
"typical_p": 1.0,
|
84 |
"use_bfloat16": false,
|
85 |
-
"
|
|
|
86 |
},
|
87 |
"text_config_dict": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
88 |
"hidden_size": 768,
|
89 |
-
"
|
90 |
-
|
91 |
-
|
92 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
93 |
},
|
94 |
"torch_dtype": "float32",
|
95 |
"transformers_version": null,
|
96 |
"vision_config": {
|
97 |
-
"_name_or_path": "",
|
98 |
"add_cross_attention": false,
|
99 |
-
"architectures":
|
|
|
|
|
100 |
"attention_dropout": 0.0,
|
101 |
"bad_words_ids": null,
|
102 |
"begin_suppress_tokens": null,
|
@@ -133,7 +218,6 @@
|
|
133 |
"layer_norm_eps": 1e-05,
|
134 |
"length_penalty": 1.0,
|
135 |
"max_length": 20,
|
136 |
-
"max_position_embeddings": 0,
|
137 |
"min_length": 0,
|
138 |
"model_type": "clip_vision_model",
|
139 |
"no_repeat_ngram_size": 0,
|
@@ -141,15 +225,16 @@
|
|
141 |
"num_beam_groups": 1,
|
142 |
"num_beams": 1,
|
143 |
"num_channels": 3,
|
144 |
-
"num_hidden_layers":
|
145 |
"num_return_sequences": 1,
|
146 |
"output_attentions": false,
|
147 |
"output_hidden_states": false,
|
148 |
"output_scores": false,
|
149 |
"pad_token_id": null,
|
150 |
-
"patch_size":
|
151 |
"prefix": null,
|
152 |
"problem_type": null,
|
|
|
153 |
"pruned_heads": {},
|
154 |
"remove_invalid_values": false,
|
155 |
"repetition_penalty": 1.0,
|
@@ -159,25 +244,380 @@
|
|
159 |
"suppress_tokens": null,
|
160 |
"task_specific_params": null,
|
161 |
"temperature": 1.0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
162 |
"tf_legacy_loss": false,
|
163 |
"tie_encoder_decoder": false,
|
164 |
"tie_word_embeddings": true,
|
165 |
"tokenizer_class": null,
|
166 |
"top_k": 50,
|
167 |
"top_p": 1.0,
|
168 |
-
"torch_dtype":
|
169 |
"torchscript": false,
|
170 |
"transformers_version": "4.24.0",
|
171 |
"typical_p": 1.0,
|
172 |
"use_bfloat16": false,
|
173 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
174 |
},
|
175 |
"vision_config_dict": {
|
176 |
-
"
|
177 |
-
"
|
178 |
-
"
|
179 |
-
|
180 |
-
|
181 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
182 |
}
|
183 |
}
|
|
|
8 |
"model_type": "clip",
|
9 |
"projection_dim": 512,
|
10 |
"text_config": {
|
11 |
+
"_name_or_path": "amir7d0/clip-text-fa",
|
12 |
"add_cross_attention": false,
|
13 |
+
"architectures": [
|
14 |
+
"RobertaModel"
|
15 |
+
],
|
16 |
"attention_dropout": 0.0,
|
17 |
+
"attention_probs_dropout_prob": 0.1,
|
18 |
"bad_words_ids": null,
|
19 |
"begin_suppress_tokens": null,
|
20 |
"bos_token_id": 0,
|
21 |
"chunk_size_feed_forward": 0,
|
22 |
+
"classifier_dropout": null,
|
23 |
"cross_attention_hidden_size": null,
|
24 |
"decoder_start_token_id": null,
|
25 |
"diversity_penalty": 0.0,
|
|
|
32 |
"finetuning_task": null,
|
33 |
"forced_bos_token_id": null,
|
34 |
"forced_eos_token_id": null,
|
35 |
+
"gradient_checkpointing": false,
|
36 |
+
"hidden_act": "gelu",
|
37 |
+
"hidden_dropout_prob": 0.1,
|
38 |
"hidden_size": 768,
|
39 |
"id2label": {
|
40 |
"0": "LABEL_0",
|
|
|
42 |
},
|
43 |
"initializer_factor": 1.0,
|
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": 514,
|
56 |
"min_length": 0,
|
57 |
"model_type": "clip_text_model",
|
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": 1,
|
68 |
+
"position_embedding_type": "absolute",
|
69 |
"prefix": null,
|
70 |
"problem_type": null,
|
71 |
"pruned_heads": {},
|
|
|
83 |
"tokenizer_class": null,
|
84 |
"top_k": 50,
|
85 |
"top_p": 1.0,
|
86 |
+
"torch_dtype": "float32",
|
87 |
"torchscript": false,
|
88 |
"transformers_version": "4.24.0",
|
89 |
+
"type_vocab_size": 1,
|
90 |
"typical_p": 1.0,
|
91 |
"use_bfloat16": false,
|
92 |
+
"use_cache": true,
|
93 |
+
"vocab_size": 42000
|
94 |
},
|
95 |
"text_config_dict": {
|
96 |
+
"_name_or_path": "amir7d0/clip-text-fa",
|
97 |
+
"add_cross_attention": false,
|
98 |
+
"architectures": [
|
99 |
+
"RobertaModel"
|
100 |
+
],
|
101 |
+
"attention_probs_dropout_prob": 0.1,
|
102 |
+
"bad_words_ids": null,
|
103 |
+
"begin_suppress_tokens": null,
|
104 |
+
"bos_token_id": 0,
|
105 |
+
"chunk_size_feed_forward": 0,
|
106 |
+
"classifier_dropout": null,
|
107 |
+
"cross_attention_hidden_size": null,
|
108 |
+
"decoder_start_token_id": null,
|
109 |
+
"diversity_penalty": 0.0,
|
110 |
+
"do_sample": false,
|
111 |
+
"early_stopping": false,
|
112 |
+
"encoder_no_repeat_ngram_size": 0,
|
113 |
+
"eos_token_id": 2,
|
114 |
+
"exponential_decay_length_penalty": null,
|
115 |
+
"finetuning_task": null,
|
116 |
+
"forced_bos_token_id": null,
|
117 |
+
"forced_eos_token_id": null,
|
118 |
+
"gradient_checkpointing": false,
|
119 |
+
"hidden_act": "gelu",
|
120 |
+
"hidden_dropout_prob": 0.1,
|
121 |
"hidden_size": 768,
|
122 |
+
"id2label": {
|
123 |
+
"0": "LABEL_0",
|
124 |
+
"1": "LABEL_1"
|
125 |
+
},
|
126 |
+
"initializer_range": 0.02,
|
127 |
+
"intermediate_size": 3072,
|
128 |
+
"is_decoder": false,
|
129 |
+
"is_encoder_decoder": false,
|
130 |
+
"label2id": {
|
131 |
+
"LABEL_0": 0,
|
132 |
+
"LABEL_1": 1
|
133 |
+
},
|
134 |
+
"layer_norm_eps": 1e-12,
|
135 |
+
"length_penalty": 1.0,
|
136 |
+
"max_length": 20,
|
137 |
+
"max_position_embeddings": 514,
|
138 |
+
"min_length": 0,
|
139 |
+
"model_type": "roberta",
|
140 |
+
"no_repeat_ngram_size": 0,
|
141 |
+
"num_attention_heads": 12,
|
142 |
+
"num_beam_groups": 1,
|
143 |
+
"num_beams": 1,
|
144 |
+
"num_hidden_layers": 12,
|
145 |
+
"num_return_sequences": 1,
|
146 |
+
"output_attentions": false,
|
147 |
+
"output_hidden_states": false,
|
148 |
+
"output_scores": false,
|
149 |
+
"pad_token_id": 1,
|
150 |
+
"position_embedding_type": "absolute",
|
151 |
+
"prefix": null,
|
152 |
+
"problem_type": null,
|
153 |
+
"pruned_heads": {},
|
154 |
+
"remove_invalid_values": false,
|
155 |
+
"repetition_penalty": 1.0,
|
156 |
+
"return_dict": true,
|
157 |
+
"return_dict_in_generate": false,
|
158 |
+
"sep_token_id": null,
|
159 |
+
"suppress_tokens": null,
|
160 |
+
"task_specific_params": null,
|
161 |
+
"temperature": 1.0,
|
162 |
+
"tf_legacy_loss": false,
|
163 |
+
"tie_encoder_decoder": false,
|
164 |
+
"tie_word_embeddings": true,
|
165 |
+
"tokenizer_class": null,
|
166 |
+
"top_k": 50,
|
167 |
+
"top_p": 1.0,
|
168 |
+
"torch_dtype": "float32",
|
169 |
+
"torchscript": false,
|
170 |
+
"transformers_version": "4.24.0",
|
171 |
+
"type_vocab_size": 1,
|
172 |
+
"typical_p": 1.0,
|
173 |
+
"use_bfloat16": false,
|
174 |
+
"use_cache": true,
|
175 |
+
"vocab_size": 42000
|
176 |
},
|
177 |
"torch_dtype": "float32",
|
178 |
"transformers_version": null,
|
179 |
"vision_config": {
|
180 |
+
"_name_or_path": "amir7d0/clip-vit-fa",
|
181 |
"add_cross_attention": false,
|
182 |
+
"architectures": [
|
183 |
+
"CLIPVisionModel"
|
184 |
+
],
|
185 |
"attention_dropout": 0.0,
|
186 |
"bad_words_ids": null,
|
187 |
"begin_suppress_tokens": null,
|
|
|
218 |
"layer_norm_eps": 1e-05,
|
219 |
"length_penalty": 1.0,
|
220 |
"max_length": 20,
|
|
|
221 |
"min_length": 0,
|
222 |
"model_type": "clip_vision_model",
|
223 |
"no_repeat_ngram_size": 0,
|
|
|
225 |
"num_beam_groups": 1,
|
226 |
"num_beams": 1,
|
227 |
"num_channels": 3,
|
228 |
+
"num_hidden_layers": 12,
|
229 |
"num_return_sequences": 1,
|
230 |
"output_attentions": false,
|
231 |
"output_hidden_states": false,
|
232 |
"output_scores": false,
|
233 |
"pad_token_id": null,
|
234 |
+
"patch_size": 32,
|
235 |
"prefix": null,
|
236 |
"problem_type": null,
|
237 |
+
"projection_dim": 512,
|
238 |
"pruned_heads": {},
|
239 |
"remove_invalid_values": false,
|
240 |
"repetition_penalty": 1.0,
|
|
|
244 |
"suppress_tokens": null,
|
245 |
"task_specific_params": null,
|
246 |
"temperature": 1.0,
|
247 |
+
"text_config": {
|
248 |
+
"_name_or_path": "",
|
249 |
+
"add_cross_attention": false,
|
250 |
+
"architectures": null,
|
251 |
+
"attention_dropout": 0.0,
|
252 |
+
"bad_words_ids": null,
|
253 |
+
"bos_token_id": 0,
|
254 |
+
"chunk_size_feed_forward": 0,
|
255 |
+
"decoder_start_token_id": null,
|
256 |
+
"diversity_penalty": 0.0,
|
257 |
+
"do_sample": false,
|
258 |
+
"dropout": 0.0,
|
259 |
+
"early_stopping": false,
|
260 |
+
"encoder_no_repeat_ngram_size": 0,
|
261 |
+
"eos_token_id": 2,
|
262 |
+
"finetuning_task": null,
|
263 |
+
"forced_bos_token_id": null,
|
264 |
+
"forced_eos_token_id": null,
|
265 |
+
"gradient_checkpointing": false,
|
266 |
+
"hidden_act": "quick_gelu",
|
267 |
+
"hidden_size": 512,
|
268 |
+
"id2label": {
|
269 |
+
"0": "LABEL_0",
|
270 |
+
"1": "LABEL_1"
|
271 |
+
},
|
272 |
+
"initializer_factor": 1.0,
|
273 |
+
"initializer_range": 0.02,
|
274 |
+
"intermediate_size": 2048,
|
275 |
+
"is_decoder": false,
|
276 |
+
"is_encoder_decoder": false,
|
277 |
+
"label2id": {
|
278 |
+
"LABEL_0": 0,
|
279 |
+
"LABEL_1": 1
|
280 |
+
},
|
281 |
+
"layer_norm_eps": 1e-05,
|
282 |
+
"length_penalty": 1.0,
|
283 |
+
"max_length": 20,
|
284 |
+
"max_position_embeddings": 77,
|
285 |
+
"min_length": 0,
|
286 |
+
"model_type": "clip_text_model",
|
287 |
+
"no_repeat_ngram_size": 0,
|
288 |
+
"num_attention_heads": 8,
|
289 |
+
"num_beam_groups": 1,
|
290 |
+
"num_beams": 1,
|
291 |
+
"num_hidden_layers": 12,
|
292 |
+
"num_return_sequences": 1,
|
293 |
+
"output_attentions": false,
|
294 |
+
"output_hidden_states": false,
|
295 |
+
"output_scores": false,
|
296 |
+
"pad_token_id": 1,
|
297 |
+
"prefix": null,
|
298 |
+
"problem_type": null,
|
299 |
+
"pruned_heads": {},
|
300 |
+
"remove_invalid_values": false,
|
301 |
+
"repetition_penalty": 1.0,
|
302 |
+
"return_dict": true,
|
303 |
+
"return_dict_in_generate": false,
|
304 |
+
"sep_token_id": null,
|
305 |
+
"task_specific_params": null,
|
306 |
+
"temperature": 1.0,
|
307 |
+
"tie_encoder_decoder": false,
|
308 |
+
"tie_word_embeddings": true,
|
309 |
+
"tokenizer_class": null,
|
310 |
+
"top_k": 50,
|
311 |
+
"top_p": 1.0,
|
312 |
+
"torchscript": false,
|
313 |
+
"transformers_version": "4.7.0.dev0",
|
314 |
+
"use_bfloat16": false,
|
315 |
+
"vocab_size": 49408
|
316 |
+
},
|
317 |
+
"text_config_dict": null,
|
318 |
"tf_legacy_loss": false,
|
319 |
"tie_encoder_decoder": false,
|
320 |
"tie_word_embeddings": true,
|
321 |
"tokenizer_class": null,
|
322 |
"top_k": 50,
|
323 |
"top_p": 1.0,
|
324 |
+
"torch_dtype": "float32",
|
325 |
"torchscript": false,
|
326 |
"transformers_version": "4.24.0",
|
327 |
"typical_p": 1.0,
|
328 |
"use_bfloat16": false,
|
329 |
+
"vision_config": {
|
330 |
+
"_name_or_path": "",
|
331 |
+
"add_cross_attention": false,
|
332 |
+
"architectures": null,
|
333 |
+
"attention_dropout": 0.0,
|
334 |
+
"bad_words_ids": null,
|
335 |
+
"bos_token_id": null,
|
336 |
+
"chunk_size_feed_forward": 0,
|
337 |
+
"decoder_start_token_id": null,
|
338 |
+
"diversity_penalty": 0.0,
|
339 |
+
"do_sample": false,
|
340 |
+
"dropout": 0.0,
|
341 |
+
"early_stopping": false,
|
342 |
+
"encoder_no_repeat_ngram_size": 0,
|
343 |
+
"eos_token_id": null,
|
344 |
+
"finetuning_task": null,
|
345 |
+
"forced_bos_token_id": null,
|
346 |
+
"forced_eos_token_id": null,
|
347 |
+
"gradient_checkpointing": false,
|
348 |
+
"hidden_act": "quick_gelu",
|
349 |
+
"hidden_size": 768,
|
350 |
+
"id2label": {
|
351 |
+
"0": "LABEL_0",
|
352 |
+
"1": "LABEL_1"
|
353 |
+
},
|
354 |
+
"image_size": 224,
|
355 |
+
"initializer_factor": 1.0,
|
356 |
+
"initializer_range": 0.02,
|
357 |
+
"intermediate_size": 3072,
|
358 |
+
"is_decoder": false,
|
359 |
+
"is_encoder_decoder": false,
|
360 |
+
"label2id": {
|
361 |
+
"LABEL_0": 0,
|
362 |
+
"LABEL_1": 1
|
363 |
+
},
|
364 |
+
"layer_norm_eps": 1e-05,
|
365 |
+
"length_penalty": 1.0,
|
366 |
+
"max_length": 20,
|
367 |
+
"min_length": 0,
|
368 |
+
"model_type": "clip_vision_model",
|
369 |
+
"no_repeat_ngram_size": 0,
|
370 |
+
"num_attention_heads": 12,
|
371 |
+
"num_beam_groups": 1,
|
372 |
+
"num_beams": 1,
|
373 |
+
"num_hidden_layers": 12,
|
374 |
+
"num_return_sequences": 1,
|
375 |
+
"output_attentions": false,
|
376 |
+
"output_hidden_states": false,
|
377 |
+
"output_scores": false,
|
378 |
+
"pad_token_id": null,
|
379 |
+
"patch_size": 32,
|
380 |
+
"prefix": null,
|
381 |
+
"problem_type": null,
|
382 |
+
"pruned_heads": {},
|
383 |
+
"remove_invalid_values": false,
|
384 |
+
"repetition_penalty": 1.0,
|
385 |
+
"return_dict": true,
|
386 |
+
"return_dict_in_generate": false,
|
387 |
+
"sep_token_id": null,
|
388 |
+
"task_specific_params": null,
|
389 |
+
"temperature": 1.0,
|
390 |
+
"tie_encoder_decoder": false,
|
391 |
+
"tie_word_embeddings": true,
|
392 |
+
"tokenizer_class": null,
|
393 |
+
"top_k": 50,
|
394 |
+
"top_p": 1.0,
|
395 |
+
"torchscript": false,
|
396 |
+
"transformers_version": "4.7.0.dev0",
|
397 |
+
"use_bfloat16": false
|
398 |
+
},
|
399 |
+
"vision_config_dict": null
|
400 |
},
|
401 |
"vision_config_dict": {
|
402 |
+
"_name_or_path": "amir7d0/clip-vit-fa",
|
403 |
+
"add_cross_attention": false,
|
404 |
+
"architectures": [
|
405 |
+
"CLIPVisionModel"
|
406 |
+
],
|
407 |
+
"attention_dropout": 0.0,
|
408 |
+
"bad_words_ids": null,
|
409 |
+
"begin_suppress_tokens": null,
|
410 |
+
"bos_token_id": null,
|
411 |
+
"chunk_size_feed_forward": 0,
|
412 |
+
"cross_attention_hidden_size": null,
|
413 |
+
"decoder_start_token_id": null,
|
414 |
+
"diversity_penalty": 0.0,
|
415 |
+
"do_sample": false,
|
416 |
+
"dropout": 0.0,
|
417 |
+
"early_stopping": false,
|
418 |
+
"encoder_no_repeat_ngram_size": 0,
|
419 |
+
"eos_token_id": null,
|
420 |
+
"exponential_decay_length_penalty": null,
|
421 |
+
"finetuning_task": null,
|
422 |
+
"forced_bos_token_id": null,
|
423 |
+
"forced_eos_token_id": null,
|
424 |
+
"hidden_act": "quick_gelu",
|
425 |
+
"hidden_size": 768,
|
426 |
+
"id2label": {
|
427 |
+
"0": "LABEL_0",
|
428 |
+
"1": "LABEL_1"
|
429 |
+
},
|
430 |
+
"image_size": 224,
|
431 |
+
"initializer_factor": 1.0,
|
432 |
+
"initializer_range": 0.02,
|
433 |
+
"intermediate_size": 3072,
|
434 |
+
"is_decoder": false,
|
435 |
+
"is_encoder_decoder": false,
|
436 |
+
"label2id": {
|
437 |
+
"LABEL_0": 0,
|
438 |
+
"LABEL_1": 1
|
439 |
+
},
|
440 |
+
"layer_norm_eps": 1e-05,
|
441 |
+
"length_penalty": 1.0,
|
442 |
+
"max_length": 20,
|
443 |
+
"min_length": 0,
|
444 |
+
"model_type": "clip_vision_model",
|
445 |
+
"no_repeat_ngram_size": 0,
|
446 |
+
"num_attention_heads": 12,
|
447 |
+
"num_beam_groups": 1,
|
448 |
+
"num_beams": 1,
|
449 |
+
"num_channels": 3,
|
450 |
+
"num_hidden_layers": 12,
|
451 |
+
"num_return_sequences": 1,
|
452 |
+
"output_attentions": false,
|
453 |
+
"output_hidden_states": false,
|
454 |
+
"output_scores": false,
|
455 |
+
"pad_token_id": null,
|
456 |
+
"patch_size": 32,
|
457 |
+
"prefix": null,
|
458 |
+
"problem_type": null,
|
459 |
+
"projection_dim": 512,
|
460 |
+
"pruned_heads": {},
|
461 |
+
"remove_invalid_values": false,
|
462 |
+
"repetition_penalty": 1.0,
|
463 |
+
"return_dict": true,
|
464 |
+
"return_dict_in_generate": false,
|
465 |
+
"sep_token_id": null,
|
466 |
+
"suppress_tokens": null,
|
467 |
+
"task_specific_params": null,
|
468 |
+
"temperature": 1.0,
|
469 |
+
"text_config": {
|
470 |
+
"_name_or_path": "",
|
471 |
+
"add_cross_attention": false,
|
472 |
+
"architectures": null,
|
473 |
+
"attention_dropout": 0.0,
|
474 |
+
"bad_words_ids": null,
|
475 |
+
"bos_token_id": 0,
|
476 |
+
"chunk_size_feed_forward": 0,
|
477 |
+
"decoder_start_token_id": null,
|
478 |
+
"diversity_penalty": 0.0,
|
479 |
+
"do_sample": false,
|
480 |
+
"dropout": 0.0,
|
481 |
+
"early_stopping": false,
|
482 |
+
"encoder_no_repeat_ngram_size": 0,
|
483 |
+
"eos_token_id": 2,
|
484 |
+
"finetuning_task": null,
|
485 |
+
"forced_bos_token_id": null,
|
486 |
+
"forced_eos_token_id": null,
|
487 |
+
"gradient_checkpointing": false,
|
488 |
+
"hidden_act": "quick_gelu",
|
489 |
+
"hidden_size": 512,
|
490 |
+
"id2label": {
|
491 |
+
"0": "LABEL_0",
|
492 |
+
"1": "LABEL_1"
|
493 |
+
},
|
494 |
+
"initializer_factor": 1.0,
|
495 |
+
"initializer_range": 0.02,
|
496 |
+
"intermediate_size": 2048,
|
497 |
+
"is_decoder": false,
|
498 |
+
"is_encoder_decoder": false,
|
499 |
+
"label2id": {
|
500 |
+
"LABEL_0": 0,
|
501 |
+
"LABEL_1": 1
|
502 |
+
},
|
503 |
+
"layer_norm_eps": 1e-05,
|
504 |
+
"length_penalty": 1.0,
|
505 |
+
"max_length": 20,
|
506 |
+
"max_position_embeddings": 77,
|
507 |
+
"min_length": 0,
|
508 |
+
"model_type": "clip_text_model",
|
509 |
+
"no_repeat_ngram_size": 0,
|
510 |
+
"num_attention_heads": 8,
|
511 |
+
"num_beam_groups": 1,
|
512 |
+
"num_beams": 1,
|
513 |
+
"num_hidden_layers": 12,
|
514 |
+
"num_return_sequences": 1,
|
515 |
+
"output_attentions": false,
|
516 |
+
"output_hidden_states": false,
|
517 |
+
"output_scores": false,
|
518 |
+
"pad_token_id": 1,
|
519 |
+
"prefix": null,
|
520 |
+
"problem_type": null,
|
521 |
+
"pruned_heads": {},
|
522 |
+
"remove_invalid_values": false,
|
523 |
+
"repetition_penalty": 1.0,
|
524 |
+
"return_dict": true,
|
525 |
+
"return_dict_in_generate": false,
|
526 |
+
"sep_token_id": null,
|
527 |
+
"task_specific_params": null,
|
528 |
+
"temperature": 1.0,
|
529 |
+
"tie_encoder_decoder": false,
|
530 |
+
"tie_word_embeddings": true,
|
531 |
+
"tokenizer_class": null,
|
532 |
+
"top_k": 50,
|
533 |
+
"top_p": 1.0,
|
534 |
+
"torchscript": false,
|
535 |
+
"transformers_version": "4.7.0.dev0",
|
536 |
+
"use_bfloat16": false,
|
537 |
+
"vocab_size": 49408
|
538 |
+
},
|
539 |
+
"text_config_dict": null,
|
540 |
+
"tf_legacy_loss": false,
|
541 |
+
"tie_encoder_decoder": false,
|
542 |
+
"tie_word_embeddings": true,
|
543 |
+
"tokenizer_class": null,
|
544 |
+
"top_k": 50,
|
545 |
+
"top_p": 1.0,
|
546 |
+
"torch_dtype": "float32",
|
547 |
+
"torchscript": false,
|
548 |
+
"transformers_version": "4.24.0",
|
549 |
+
"typical_p": 1.0,
|
550 |
+
"use_bfloat16": false,
|
551 |
+
"vision_config": {
|
552 |
+
"_name_or_path": "",
|
553 |
+
"add_cross_attention": false,
|
554 |
+
"architectures": null,
|
555 |
+
"attention_dropout": 0.0,
|
556 |
+
"bad_words_ids": null,
|
557 |
+
"bos_token_id": null,
|
558 |
+
"chunk_size_feed_forward": 0,
|
559 |
+
"decoder_start_token_id": null,
|
560 |
+
"diversity_penalty": 0.0,
|
561 |
+
"do_sample": false,
|
562 |
+
"dropout": 0.0,
|
563 |
+
"early_stopping": false,
|
564 |
+
"encoder_no_repeat_ngram_size": 0,
|
565 |
+
"eos_token_id": null,
|
566 |
+
"finetuning_task": null,
|
567 |
+
"forced_bos_token_id": null,
|
568 |
+
"forced_eos_token_id": null,
|
569 |
+
"gradient_checkpointing": false,
|
570 |
+
"hidden_act": "quick_gelu",
|
571 |
+
"hidden_size": 768,
|
572 |
+
"id2label": {
|
573 |
+
"0": "LABEL_0",
|
574 |
+
"1": "LABEL_1"
|
575 |
+
},
|
576 |
+
"image_size": 224,
|
577 |
+
"initializer_factor": 1.0,
|
578 |
+
"initializer_range": 0.02,
|
579 |
+
"intermediate_size": 3072,
|
580 |
+
"is_decoder": false,
|
581 |
+
"is_encoder_decoder": false,
|
582 |
+
"label2id": {
|
583 |
+
"LABEL_0": 0,
|
584 |
+
"LABEL_1": 1
|
585 |
+
},
|
586 |
+
"layer_norm_eps": 1e-05,
|
587 |
+
"length_penalty": 1.0,
|
588 |
+
"max_length": 20,
|
589 |
+
"min_length": 0,
|
590 |
+
"model_type": "clip_vision_model",
|
591 |
+
"no_repeat_ngram_size": 0,
|
592 |
+
"num_attention_heads": 12,
|
593 |
+
"num_beam_groups": 1,
|
594 |
+
"num_beams": 1,
|
595 |
+
"num_hidden_layers": 12,
|
596 |
+
"num_return_sequences": 1,
|
597 |
+
"output_attentions": false,
|
598 |
+
"output_hidden_states": false,
|
599 |
+
"output_scores": false,
|
600 |
+
"pad_token_id": null,
|
601 |
+
"patch_size": 32,
|
602 |
+
"prefix": null,
|
603 |
+
"problem_type": null,
|
604 |
+
"pruned_heads": {},
|
605 |
+
"remove_invalid_values": false,
|
606 |
+
"repetition_penalty": 1.0,
|
607 |
+
"return_dict": true,
|
608 |
+
"return_dict_in_generate": false,
|
609 |
+
"sep_token_id": null,
|
610 |
+
"task_specific_params": null,
|
611 |
+
"temperature": 1.0,
|
612 |
+
"tie_encoder_decoder": false,
|
613 |
+
"tie_word_embeddings": true,
|
614 |
+
"tokenizer_class": null,
|
615 |
+
"top_k": 50,
|
616 |
+
"top_p": 1.0,
|
617 |
+
"torchscript": false,
|
618 |
+
"transformers_version": "4.7.0.dev0",
|
619 |
+
"use_bfloat16": false
|
620 |
+
},
|
621 |
+
"vision_config_dict": null
|
622 |
}
|
623 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72e2aa2c90242720595c6e78515ca21e9e704c96d60f51215157ccc1172ea5f0
|
3 |
+
size 826305627
|