root commited on
Commit ·
9f2f03e
1
Parent(s): b870f96
model trained
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- 1/config.json +165 -0
- 1/flax_model.msgpack +3 -0
- 10/config.json +165 -0
- 10/flax_model.msgpack +3 -0
- 11/config.json +165 -0
- 11/flax_model.msgpack +3 -0
- 12/config.json +165 -0
- 12/flax_model.msgpack +3 -0
- 13/config.json +165 -0
- 13/flax_model.msgpack +3 -0
- 14/config.json +165 -0
- 14/flax_model.msgpack +3 -0
- 15/config.json +165 -0
- 15/flax_model.msgpack +3 -0
- 16/config.json +165 -0
- 16/flax_model.msgpack +3 -0
- 17/config.json +165 -0
- 17/flax_model.msgpack +3 -0
- 18/config.json +165 -0
- 18/flax_model.msgpack +3 -0
- 19/config.json +165 -0
- 19/flax_model.msgpack +3 -0
- 2/config.json +165 -0
- 2/flax_model.msgpack +3 -0
- 20/config.json +165 -0
- 20/flax_model.msgpack +3 -0
- 21/config.json +165 -0
- 21/flax_model.msgpack +3 -0
- 22/config.json +165 -0
- 22/flax_model.msgpack +3 -0
- 23/config.json +165 -0
- 23/flax_model.msgpack +3 -0
- 24/config.json +165 -0
- 24/flax_model.msgpack +3 -0
- 25/config.json +165 -0
- 25/flax_model.msgpack +3 -0
- 26/config.json +165 -0
- 26/flax_model.msgpack +3 -0
- 27/config.json +165 -0
- 27/flax_model.msgpack +3 -0
- 28/config.json +165 -0
- 28/flax_model.msgpack +3 -0
- 29/config.json +165 -0
- 29/flax_model.msgpack +3 -0
- 3/config.json +165 -0
- 3/flax_model.msgpack +3 -0
- 30/config.json +165 -0
- 30/flax_model.msgpack +3 -0
- 31/config.json +165 -0
- 31/flax_model.msgpack +3 -0
1/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
1/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91cd41430a21f5f850e84ab107ee2281636640f8d2f10d3bbc7875e14fb206d8
|
| 3 |
+
size 851566424
|
10/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
10/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b688e9d1ef5523d69e490937244975a71454881100aa56fa082748d5b9b62c6
|
| 3 |
+
size 851566424
|
11/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
11/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b60c73ee8849789a0b7ba9a65fcf4cc0d965fe5c6436a1fe230e9d85810e0b58
|
| 3 |
+
size 851566424
|
12/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
12/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c8f1cd5748f54256a4744259f8d6e4c3c65aa004f3a6242c6e8acc719aa9111
|
| 3 |
+
size 851566424
|
13/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
13/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8af15b2801ee72b348cdb5770dbf25f4e5991e59a5cb029a8c944ca754d631d7
|
| 3 |
+
size 851566424
|
14/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
14/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce27ac2af40bf4b90376d5889677a2570f972c1e0130c981bc560341f1bfd65e
|
| 3 |
+
size 851566424
|
15/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
15/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:240f4fe5dc0f40f2d8e31525c2ac761931e30c1d066f802b82c3190428b4ccd7
|
| 3 |
+
size 851566424
|
16/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
16/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08a518c66ea64d7e493d11860c03663754e075a5876de0eeb1c1c43b0271f2da
|
| 3 |
+
size 851566424
|
17/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
17/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5f36850f2a1194bb5af12e8ded20ba4c8e832c4b1d8df3af94d8a62e4d04053
|
| 3 |
+
size 851566424
|
18/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
18/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8012d67d5a34acb9d5f46667470699b7817022b2fcda1149cd31697a6434ab0e
|
| 3 |
+
size 851566424
|
19/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
19/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50a23bd5420080cff32928c6b9ef894453b874070bbd0af2b9d4c604b2207919
|
| 3 |
+
size 851566424
|
2/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
2/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:647efee73c66ba3fc8bbba7ef96919da8131a861bb8ab6f8c84b5434db1032ae
|
| 3 |
+
size 851566424
|
20/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
20/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:451369296e56171b88aa429326fd651e3096dc3eaac978292efba28e4e819128
|
| 3 |
+
size 851566424
|
21/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
21/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4cf0fdd2cec8ace7a7bb7c7f4d2b293e90408324f04f00fe920198d228e989c1
|
| 3 |
+
size 851566424
|
22/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
22/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f836c3f07e91793323df1243e7b012fdf45928c60b5218fe408a364430d4e5c
|
| 3 |
+
size 851566424
|
23/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
23/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cf416daa7d9cf87ae89e19b86be8957163f2bd8af81bfe60d96a32ee43e7d22
|
| 3 |
+
size 851566424
|
24/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
24/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:53f577daf549fe9fad8ee3ddb3fc4cb780928a900c4b5f9358182c2bc6f89d1c
|
| 3 |
+
size 851566424
|
25/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
25/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9453ca5687afdec8f8385a06cebaaf5a1cdbd0b5b1c0bb78c45484f2d9d99e9f
|
| 3 |
+
size 851566424
|
26/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
26/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a84673136aeb0c9cd982bf87a641f91b5ab000ea0494b06bf66467c7904dea5
|
| 3 |
+
size 851566424
|
27/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
27/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d450f443e9bac3880d7fb7e9def53ea9beeb4131c7cc9820239324c464e0deb
|
| 3 |
+
size 851566424
|
28/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
28/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc9a81871888bd762b062803b48bd29ebe0f1ffb137c6a27dbea3a4ce4051f74
|
| 3 |
+
size 851566424
|
29/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
29/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f26c98d8c38248c43ac6c4780e4093d8c2b6600d6c8213db6417143c8944bf7
|
| 3 |
+
size 851566424
|
3/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
3/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dee95fec2497d4a6726d7705af060f7be41cb9ce80372161a50367d4a85c09da
|
| 3 |
+
size 851566424
|
30/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
30/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1eb23f45c56415e8bc3b1f6389a18ffd2ceaf90da78f6b59db7b2ba84cb6440a
|
| 3 |
+
size 851566424
|
31/config.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"HybridCLIP"
|
| 4 |
+
],
|
| 5 |
+
"freeze_backbones": false,
|
| 6 |
+
"initializer_factor": 1.0,
|
| 7 |
+
"model_type": "hybrid-clip",
|
| 8 |
+
"projection_dim": 512,
|
| 9 |
+
"seed": 42,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"_name_or_path": "roberta-base",
|
| 12 |
+
"add_cross_attention": false,
|
| 13 |
+
"architectures": [
|
| 14 |
+
"RobertaForMaskedLM"
|
| 15 |
+
],
|
| 16 |
+
"attention_probs_dropout_prob": 0.1,
|
| 17 |
+
"bad_words_ids": null,
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"chunk_size_feed_forward": 0,
|
| 20 |
+
"classifier_dropout": null,
|
| 21 |
+
"cross_attention_hidden_size": null,
|
| 22 |
+
"decoder_start_token_id": null,
|
| 23 |
+
"diversity_penalty": 0.0,
|
| 24 |
+
"do_sample": false,
|
| 25 |
+
"early_stopping": false,
|
| 26 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 27 |
+
"eos_token_id": 2,
|
| 28 |
+
"exponential_decay_length_penalty": null,
|
| 29 |
+
"finetuning_task": null,
|
| 30 |
+
"forced_bos_token_id": null,
|
| 31 |
+
"forced_eos_token_id": null,
|
| 32 |
+
"hidden_act": "gelu",
|
| 33 |
+
"hidden_dropout_prob": 0.1,
|
| 34 |
+
"hidden_size": 768,
|
| 35 |
+
"id2label": {
|
| 36 |
+
"0": "LABEL_0",
|
| 37 |
+
"1": "LABEL_1"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 3072,
|
| 41 |
+
"is_decoder": false,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_norm_eps": 1e-05,
|
| 48 |
+
"length_penalty": 1.0,
|
| 49 |
+
"max_length": 20,
|
| 50 |
+
"max_position_embeddings": 514,
|
| 51 |
+
"min_length": 0,
|
| 52 |
+
"model_type": "roberta",
|
| 53 |
+
"no_repeat_ngram_size": 0,
|
| 54 |
+
"num_attention_heads": 12,
|
| 55 |
+
"num_beam_groups": 1,
|
| 56 |
+
"num_beams": 1,
|
| 57 |
+
"num_hidden_layers": 12,
|
| 58 |
+
"num_return_sequences": 1,
|
| 59 |
+
"output_attentions": false,
|
| 60 |
+
"output_hidden_states": false,
|
| 61 |
+
"output_scores": false,
|
| 62 |
+
"pad_token_id": 1,
|
| 63 |
+
"position_embedding_type": "absolute",
|
| 64 |
+
"prefix": null,
|
| 65 |
+
"problem_type": null,
|
| 66 |
+
"pruned_heads": {},
|
| 67 |
+
"remove_invalid_values": false,
|
| 68 |
+
"repetition_penalty": 1.0,
|
| 69 |
+
"return_dict": true,
|
| 70 |
+
"return_dict_in_generate": false,
|
| 71 |
+
"sep_token_id": null,
|
| 72 |
+
"task_specific_params": null,
|
| 73 |
+
"temperature": 1.0,
|
| 74 |
+
"tf_legacy_loss": false,
|
| 75 |
+
"tie_encoder_decoder": false,
|
| 76 |
+
"tie_word_embeddings": true,
|
| 77 |
+
"tokenizer_class": null,
|
| 78 |
+
"top_k": 50,
|
| 79 |
+
"top_p": 1.0,
|
| 80 |
+
"torch_dtype": null,
|
| 81 |
+
"torchscript": false,
|
| 82 |
+
"transformers_version": "4.21.0",
|
| 83 |
+
"type_vocab_size": 1,
|
| 84 |
+
"typical_p": 1.0,
|
| 85 |
+
"use_bfloat16": false,
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"vocab_size": 50265
|
| 88 |
+
},
|
| 89 |
+
"transformers_version": null,
|
| 90 |
+
"vision_config": {
|
| 91 |
+
"_name_or_path": "",
|
| 92 |
+
"add_cross_attention": false,
|
| 93 |
+
"architectures": null,
|
| 94 |
+
"attention_dropout": 0.0,
|
| 95 |
+
"bad_words_ids": null,
|
| 96 |
+
"bos_token_id": null,
|
| 97 |
+
"chunk_size_feed_forward": 0,
|
| 98 |
+
"cross_attention_hidden_size": null,
|
| 99 |
+
"decoder_start_token_id": null,
|
| 100 |
+
"diversity_penalty": 0.0,
|
| 101 |
+
"do_sample": false,
|
| 102 |
+
"dropout": 0.0,
|
| 103 |
+
"early_stopping": false,
|
| 104 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 105 |
+
"eos_token_id": null,
|
| 106 |
+
"exponential_decay_length_penalty": null,
|
| 107 |
+
"finetuning_task": null,
|
| 108 |
+
"forced_bos_token_id": null,
|
| 109 |
+
"forced_eos_token_id": null,
|
| 110 |
+
"hidden_act": "quick_gelu",
|
| 111 |
+
"hidden_size": 768,
|
| 112 |
+
"id2label": {
|
| 113 |
+
"0": "LABEL_0",
|
| 114 |
+
"1": "LABEL_1"
|
| 115 |
+
},
|
| 116 |
+
"image_size": 224,
|
| 117 |
+
"initializer_factor": 1.0,
|
| 118 |
+
"initializer_range": 0.02,
|
| 119 |
+
"intermediate_size": 3072,
|
| 120 |
+
"is_decoder": false,
|
| 121 |
+
"is_encoder_decoder": false,
|
| 122 |
+
"label2id": {
|
| 123 |
+
"LABEL_0": 0,
|
| 124 |
+
"LABEL_1": 1
|
| 125 |
+
},
|
| 126 |
+
"layer_norm_eps": 1e-05,
|
| 127 |
+
"length_penalty": 1.0,
|
| 128 |
+
"max_length": 20,
|
| 129 |
+
"min_length": 0,
|
| 130 |
+
"model_type": "clip_vision_model",
|
| 131 |
+
"no_repeat_ngram_size": 0,
|
| 132 |
+
"num_attention_heads": 12,
|
| 133 |
+
"num_beam_groups": 1,
|
| 134 |
+
"num_beams": 1,
|
| 135 |
+
"num_channels": 3,
|
| 136 |
+
"num_hidden_layers": 12,
|
| 137 |
+
"num_return_sequences": 1,
|
| 138 |
+
"output_attentions": false,
|
| 139 |
+
"output_hidden_states": false,
|
| 140 |
+
"output_scores": false,
|
| 141 |
+
"pad_token_id": null,
|
| 142 |
+
"patch_size": 32,
|
| 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 |
+
"sep_token_id": null,
|
| 151 |
+
"task_specific_params": null,
|
| 152 |
+
"temperature": 1.0,
|
| 153 |
+
"tf_legacy_loss": false,
|
| 154 |
+
"tie_encoder_decoder": false,
|
| 155 |
+
"tie_word_embeddings": true,
|
| 156 |
+
"tokenizer_class": null,
|
| 157 |
+
"top_k": 50,
|
| 158 |
+
"top_p": 1.0,
|
| 159 |
+
"torch_dtype": null,
|
| 160 |
+
"torchscript": false,
|
| 161 |
+
"transformers_version": "4.21.0",
|
| 162 |
+
"typical_p": 1.0,
|
| 163 |
+
"use_bfloat16": false
|
| 164 |
+
}
|
| 165 |
+
}
|
31/flax_model.msgpack
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72b6763a3d623e9ad3ca68964705d1343d47f264bb43fda597ebd8c30efd23e2
|
| 3 |
+
size 851566424
|