V4.22.0 update
Browse files- config.json +38 -22
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -1,4 +1,8 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"initializer_factor": 1.0,
|
| 3 |
"logit_scale_init_value": 2.6592,
|
| 4 |
"model_type": "clip",
|
|
@@ -7,21 +11,22 @@
|
|
| 7 |
"_name_or_path": "",
|
| 8 |
"add_cross_attention": false,
|
| 9 |
"architectures": null,
|
| 10 |
-
"attention_dropout": 0.
|
| 11 |
"bad_words_ids": null,
|
| 12 |
"bos_token_id": 0,
|
| 13 |
"chunk_size_feed_forward": 0,
|
|
|
|
| 14 |
"decoder_start_token_id": null,
|
| 15 |
"diversity_penalty": 0.0,
|
| 16 |
"do_sample": false,
|
| 17 |
-
"dropout": 0.
|
| 18 |
"early_stopping": false,
|
| 19 |
"encoder_no_repeat_ngram_size": 0,
|
| 20 |
"eos_token_id": 2,
|
|
|
|
| 21 |
"finetuning_task": null,
|
| 22 |
"forced_bos_token_id": null,
|
| 23 |
"forced_eos_token_id": null,
|
| 24 |
-
"gradient_checkpointing": false,
|
| 25 |
"hidden_act": "quick_gelu",
|
| 26 |
"hidden_size": 32,
|
| 27 |
"id2label": {
|
|
@@ -40,7 +45,7 @@
|
|
| 40 |
"layer_norm_eps": 1e-05,
|
| 41 |
"length_penalty": 1.0,
|
| 42 |
"max_length": 20,
|
| 43 |
-
"max_position_embeddings":
|
| 44 |
"min_length": 0,
|
| 45 |
"model_type": "clip_text_model",
|
| 46 |
"no_repeat_ngram_size": 0,
|
|
@@ -63,6 +68,7 @@
|
|
| 63 |
"sep_token_id": null,
|
| 64 |
"task_specific_params": null,
|
| 65 |
"temperature": 1.0,
|
|
|
|
| 66 |
"tie_encoder_decoder": false,
|
| 67 |
"tie_word_embeddings": true,
|
| 68 |
"tokenizer_class": null,
|
|
@@ -70,29 +76,31 @@
|
|
| 70 |
"top_p": 1.0,
|
| 71 |
"torch_dtype": null,
|
| 72 |
"torchscript": false,
|
| 73 |
-
"transformers_version": "4.
|
|
|
|
| 74 |
"use_bfloat16": false,
|
| 75 |
-
"vocab_size":
|
| 76 |
},
|
| 77 |
"text_config_dict": {
|
| 78 |
"_name_or_path": "",
|
| 79 |
"add_cross_attention": false,
|
| 80 |
"architectures": null,
|
| 81 |
-
"attention_dropout": 0.
|
| 82 |
"bad_words_ids": null,
|
| 83 |
"bos_token_id": 0,
|
| 84 |
"chunk_size_feed_forward": 0,
|
|
|
|
| 85 |
"decoder_start_token_id": null,
|
| 86 |
"diversity_penalty": 0.0,
|
| 87 |
"do_sample": false,
|
| 88 |
-
"dropout": 0.
|
| 89 |
"early_stopping": false,
|
| 90 |
"encoder_no_repeat_ngram_size": 0,
|
| 91 |
"eos_token_id": 2,
|
|
|
|
| 92 |
"finetuning_task": null,
|
| 93 |
"forced_bos_token_id": null,
|
| 94 |
"forced_eos_token_id": null,
|
| 95 |
-
"gradient_checkpointing": false,
|
| 96 |
"hidden_act": "quick_gelu",
|
| 97 |
"hidden_size": 32,
|
| 98 |
"id2label": {
|
|
@@ -111,7 +119,7 @@
|
|
| 111 |
"layer_norm_eps": 1e-05,
|
| 112 |
"length_penalty": 1.0,
|
| 113 |
"max_length": 20,
|
| 114 |
-
"max_position_embeddings":
|
| 115 |
"min_length": 0,
|
| 116 |
"model_type": "clip_text_model",
|
| 117 |
"no_repeat_ngram_size": 0,
|
|
@@ -134,6 +142,7 @@
|
|
| 134 |
"sep_token_id": null,
|
| 135 |
"task_specific_params": null,
|
| 136 |
"temperature": 1.0,
|
|
|
|
| 137 |
"tie_encoder_decoder": false,
|
| 138 |
"tie_word_embeddings": true,
|
| 139 |
"tokenizer_class": null,
|
|
@@ -141,30 +150,33 @@
|
|
| 141 |
"top_p": 1.0,
|
| 142 |
"torch_dtype": null,
|
| 143 |
"torchscript": false,
|
| 144 |
-
"transformers_version": "4.
|
|
|
|
| 145 |
"use_bfloat16": false,
|
| 146 |
-
"vocab_size":
|
| 147 |
},
|
|
|
|
| 148 |
"transformers_version": null,
|
| 149 |
"vision_config": {
|
| 150 |
"_name_or_path": "",
|
| 151 |
"add_cross_attention": false,
|
| 152 |
"architectures": null,
|
| 153 |
-
"attention_dropout": 0.
|
| 154 |
"bad_words_ids": null,
|
| 155 |
"bos_token_id": null,
|
| 156 |
"chunk_size_feed_forward": 0,
|
|
|
|
| 157 |
"decoder_start_token_id": null,
|
| 158 |
"diversity_penalty": 0.0,
|
| 159 |
"do_sample": false,
|
| 160 |
-
"dropout": 0.
|
| 161 |
"early_stopping": false,
|
| 162 |
"encoder_no_repeat_ngram_size": 0,
|
| 163 |
"eos_token_id": null,
|
|
|
|
| 164 |
"finetuning_task": null,
|
| 165 |
"forced_bos_token_id": null,
|
| 166 |
"forced_eos_token_id": null,
|
| 167 |
-
"gradient_checkpointing": false,
|
| 168 |
"hidden_act": "quick_gelu",
|
| 169 |
"hidden_size": 32,
|
| 170 |
"id2label": {
|
|
@@ -208,6 +220,7 @@
|
|
| 208 |
"sep_token_id": null,
|
| 209 |
"task_specific_params": null,
|
| 210 |
"temperature": 1.0,
|
|
|
|
| 211 |
"tie_encoder_decoder": false,
|
| 212 |
"tie_word_embeddings": true,
|
| 213 |
"tokenizer_class": null,
|
|
@@ -215,28 +228,30 @@
|
|
| 215 |
"top_p": 1.0,
|
| 216 |
"torch_dtype": null,
|
| 217 |
"torchscript": false,
|
| 218 |
-
"transformers_version": "4.
|
|
|
|
| 219 |
"use_bfloat16": false
|
| 220 |
},
|
| 221 |
"vision_config_dict": {
|
| 222 |
"_name_or_path": "",
|
| 223 |
"add_cross_attention": false,
|
| 224 |
"architectures": null,
|
| 225 |
-
"attention_dropout": 0.
|
| 226 |
"bad_words_ids": null,
|
| 227 |
"bos_token_id": null,
|
| 228 |
"chunk_size_feed_forward": 0,
|
|
|
|
| 229 |
"decoder_start_token_id": null,
|
| 230 |
"diversity_penalty": 0.0,
|
| 231 |
"do_sample": false,
|
| 232 |
-
"dropout": 0.
|
| 233 |
"early_stopping": false,
|
| 234 |
"encoder_no_repeat_ngram_size": 0,
|
| 235 |
"eos_token_id": null,
|
|
|
|
| 236 |
"finetuning_task": null,
|
| 237 |
"forced_bos_token_id": null,
|
| 238 |
"forced_eos_token_id": null,
|
| 239 |
-
"gradient_checkpointing": false,
|
| 240 |
"hidden_act": "quick_gelu",
|
| 241 |
"hidden_size": 32,
|
| 242 |
"id2label": {
|
|
@@ -280,6 +295,7 @@
|
|
| 280 |
"sep_token_id": null,
|
| 281 |
"task_specific_params": null,
|
| 282 |
"temperature": 1.0,
|
|
|
|
| 283 |
"tie_encoder_decoder": false,
|
| 284 |
"tie_word_embeddings": true,
|
| 285 |
"tokenizer_class": null,
|
|
@@ -287,8 +303,8 @@
|
|
| 287 |
"top_p": 1.0,
|
| 288 |
"torch_dtype": null,
|
| 289 |
"torchscript": false,
|
| 290 |
-
"transformers_version": "4.
|
|
|
|
| 291 |
"use_bfloat16": false
|
| 292 |
-
}
|
| 293 |
-
"vocab_size": 1000
|
| 294 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_commit_hash": null,
|
| 3 |
+
"architectures": [
|
| 4 |
+
"CLIPModel"
|
| 5 |
+
],
|
| 6 |
"initializer_factor": 1.0,
|
| 7 |
"logit_scale_init_value": 2.6592,
|
| 8 |
"model_type": "clip",
|
|
|
|
| 11 |
"_name_or_path": "",
|
| 12 |
"add_cross_attention": false,
|
| 13 |
"architectures": null,
|
| 14 |
+
"attention_dropout": 0.0,
|
| 15 |
"bad_words_ids": null,
|
| 16 |
"bos_token_id": 0,
|
| 17 |
"chunk_size_feed_forward": 0,
|
| 18 |
+
"cross_attention_hidden_size": null,
|
| 19 |
"decoder_start_token_id": null,
|
| 20 |
"diversity_penalty": 0.0,
|
| 21 |
"do_sample": false,
|
| 22 |
+
"dropout": 0.0,
|
| 23 |
"early_stopping": false,
|
| 24 |
"encoder_no_repeat_ngram_size": 0,
|
| 25 |
"eos_token_id": 2,
|
| 26 |
+
"exponential_decay_length_penalty": null,
|
| 27 |
"finetuning_task": null,
|
| 28 |
"forced_bos_token_id": null,
|
| 29 |
"forced_eos_token_id": null,
|
|
|
|
| 30 |
"hidden_act": "quick_gelu",
|
| 31 |
"hidden_size": 32,
|
| 32 |
"id2label": {
|
|
|
|
| 45 |
"layer_norm_eps": 1e-05,
|
| 46 |
"length_penalty": 1.0,
|
| 47 |
"max_length": 20,
|
| 48 |
+
"max_position_embeddings": 77,
|
| 49 |
"min_length": 0,
|
| 50 |
"model_type": "clip_text_model",
|
| 51 |
"no_repeat_ngram_size": 0,
|
|
|
|
| 68 |
"sep_token_id": null,
|
| 69 |
"task_specific_params": null,
|
| 70 |
"temperature": 1.0,
|
| 71 |
+
"tf_legacy_loss": false,
|
| 72 |
"tie_encoder_decoder": false,
|
| 73 |
"tie_word_embeddings": true,
|
| 74 |
"tokenizer_class": null,
|
|
|
|
| 76 |
"top_p": 1.0,
|
| 77 |
"torch_dtype": null,
|
| 78 |
"torchscript": false,
|
| 79 |
+
"transformers_version": "4.22.0.dev0",
|
| 80 |
+
"typical_p": 1.0,
|
| 81 |
"use_bfloat16": false,
|
| 82 |
+
"vocab_size": 49408
|
| 83 |
},
|
| 84 |
"text_config_dict": {
|
| 85 |
"_name_or_path": "",
|
| 86 |
"add_cross_attention": false,
|
| 87 |
"architectures": null,
|
| 88 |
+
"attention_dropout": 0.0,
|
| 89 |
"bad_words_ids": null,
|
| 90 |
"bos_token_id": 0,
|
| 91 |
"chunk_size_feed_forward": 0,
|
| 92 |
+
"cross_attention_hidden_size": null,
|
| 93 |
"decoder_start_token_id": null,
|
| 94 |
"diversity_penalty": 0.0,
|
| 95 |
"do_sample": false,
|
| 96 |
+
"dropout": 0.0,
|
| 97 |
"early_stopping": false,
|
| 98 |
"encoder_no_repeat_ngram_size": 0,
|
| 99 |
"eos_token_id": 2,
|
| 100 |
+
"exponential_decay_length_penalty": null,
|
| 101 |
"finetuning_task": null,
|
| 102 |
"forced_bos_token_id": null,
|
| 103 |
"forced_eos_token_id": null,
|
|
|
|
| 104 |
"hidden_act": "quick_gelu",
|
| 105 |
"hidden_size": 32,
|
| 106 |
"id2label": {
|
|
|
|
| 119 |
"layer_norm_eps": 1e-05,
|
| 120 |
"length_penalty": 1.0,
|
| 121 |
"max_length": 20,
|
| 122 |
+
"max_position_embeddings": 77,
|
| 123 |
"min_length": 0,
|
| 124 |
"model_type": "clip_text_model",
|
| 125 |
"no_repeat_ngram_size": 0,
|
|
|
|
| 142 |
"sep_token_id": null,
|
| 143 |
"task_specific_params": null,
|
| 144 |
"temperature": 1.0,
|
| 145 |
+
"tf_legacy_loss": false,
|
| 146 |
"tie_encoder_decoder": false,
|
| 147 |
"tie_word_embeddings": true,
|
| 148 |
"tokenizer_class": null,
|
|
|
|
| 150 |
"top_p": 1.0,
|
| 151 |
"torch_dtype": null,
|
| 152 |
"torchscript": false,
|
| 153 |
+
"transformers_version": "4.22.0.dev0",
|
| 154 |
+
"typical_p": 1.0,
|
| 155 |
"use_bfloat16": false,
|
| 156 |
+
"vocab_size": 49408
|
| 157 |
},
|
| 158 |
+
"torch_dtype": "float32",
|
| 159 |
"transformers_version": null,
|
| 160 |
"vision_config": {
|
| 161 |
"_name_or_path": "",
|
| 162 |
"add_cross_attention": false,
|
| 163 |
"architectures": null,
|
| 164 |
+
"attention_dropout": 0.0,
|
| 165 |
"bad_words_ids": null,
|
| 166 |
"bos_token_id": null,
|
| 167 |
"chunk_size_feed_forward": 0,
|
| 168 |
+
"cross_attention_hidden_size": null,
|
| 169 |
"decoder_start_token_id": null,
|
| 170 |
"diversity_penalty": 0.0,
|
| 171 |
"do_sample": false,
|
| 172 |
+
"dropout": 0.0,
|
| 173 |
"early_stopping": false,
|
| 174 |
"encoder_no_repeat_ngram_size": 0,
|
| 175 |
"eos_token_id": null,
|
| 176 |
+
"exponential_decay_length_penalty": null,
|
| 177 |
"finetuning_task": null,
|
| 178 |
"forced_bos_token_id": null,
|
| 179 |
"forced_eos_token_id": null,
|
|
|
|
| 180 |
"hidden_act": "quick_gelu",
|
| 181 |
"hidden_size": 32,
|
| 182 |
"id2label": {
|
|
|
|
| 220 |
"sep_token_id": null,
|
| 221 |
"task_specific_params": null,
|
| 222 |
"temperature": 1.0,
|
| 223 |
+
"tf_legacy_loss": false,
|
| 224 |
"tie_encoder_decoder": false,
|
| 225 |
"tie_word_embeddings": true,
|
| 226 |
"tokenizer_class": null,
|
|
|
|
| 228 |
"top_p": 1.0,
|
| 229 |
"torch_dtype": null,
|
| 230 |
"torchscript": false,
|
| 231 |
+
"transformers_version": "4.22.0.dev0",
|
| 232 |
+
"typical_p": 1.0,
|
| 233 |
"use_bfloat16": false
|
| 234 |
},
|
| 235 |
"vision_config_dict": {
|
| 236 |
"_name_or_path": "",
|
| 237 |
"add_cross_attention": false,
|
| 238 |
"architectures": null,
|
| 239 |
+
"attention_dropout": 0.0,
|
| 240 |
"bad_words_ids": null,
|
| 241 |
"bos_token_id": null,
|
| 242 |
"chunk_size_feed_forward": 0,
|
| 243 |
+
"cross_attention_hidden_size": null,
|
| 244 |
"decoder_start_token_id": null,
|
| 245 |
"diversity_penalty": 0.0,
|
| 246 |
"do_sample": false,
|
| 247 |
+
"dropout": 0.0,
|
| 248 |
"early_stopping": false,
|
| 249 |
"encoder_no_repeat_ngram_size": 0,
|
| 250 |
"eos_token_id": null,
|
| 251 |
+
"exponential_decay_length_penalty": null,
|
| 252 |
"finetuning_task": null,
|
| 253 |
"forced_bos_token_id": null,
|
| 254 |
"forced_eos_token_id": null,
|
|
|
|
| 255 |
"hidden_act": "quick_gelu",
|
| 256 |
"hidden_size": 32,
|
| 257 |
"id2label": {
|
|
|
|
| 295 |
"sep_token_id": null,
|
| 296 |
"task_specific_params": null,
|
| 297 |
"temperature": 1.0,
|
| 298 |
+
"tf_legacy_loss": false,
|
| 299 |
"tie_encoder_decoder": false,
|
| 300 |
"tie_word_embeddings": true,
|
| 301 |
"tokenizer_class": null,
|
|
|
|
| 303 |
"top_p": 1.0,
|
| 304 |
"torch_dtype": null,
|
| 305 |
"torchscript": false,
|
| 306 |
+
"transformers_version": "4.22.0.dev0",
|
| 307 |
+
"typical_p": 1.0,
|
| 308 |
"use_bfloat16": false
|
| 309 |
+
}
|
|
|
|
| 310 |
}
|
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:fd463d8581f5032d0cc194068b4b8e05d5489b4b8478ca92368bac42d8ad4a48
|
| 3 |
+
size 6711073
|