CoolFace
Modelpublic

hf-tiny-model-private/tiny-random-VisionTextDualEncoderModel-vit-bert

sourceHugging Faceupdated 3y agoView on Hugging Face
0likes18downloads
config.json174 linesDownload Raw Back to root
1{2  "_commit_hash": null,3  "_name_or_path": "tiny_models/vision-text-dual-encoder/VisionTextDualEncoderModel-vit-bert",4  "architectures": [5    "VisionTextDualEncoderModel"6  ],7  "logit_scale_init_value": 2.6592,8  "model_type": "vision-text-dual-encoder",9  "projection_dim": 512,10  "text_config": {11    "_name_or_path": "/tmp/tmphwq2c69y/decoder/BertModel",12    "add_cross_attention": false,13    "architectures": [14      "BertModel"15    ],16    "attention_probs_dropout_prob": 0.1,17    "bad_words_ids": null,18    "begin_suppress_tokens": null,19    "bos_token_id": null,20    "chunk_size_feed_forward": 0,21    "classifier_dropout": null,22    "cross_attention_hidden_size": null,23    "decoder_start_token_id": null,24    "diversity_penalty": 0.0,25    "do_sample": false,26    "early_stopping": false,27    "encoder_no_repeat_ngram_size": 0,28    "eos_token_id": null,29    "exponential_decay_length_penalty": null,30    "finetuning_task": null,31    "forced_bos_token_id": null,32    "forced_eos_token_id": null,33    "hidden_act": "gelu",34    "hidden_dropout_prob": 0.1,35    "hidden_size": 32,36    "id2label": {37      "0": "LABEL_0",38      "1": "LABEL_1"39    },40    "initializer_range": 0.02,41    "intermediate_size": 37,42    "is_decoder": false,43    "is_encoder_decoder": false,44    "label2id": {45      "LABEL_0": 0,46      "LABEL_1": 147    },48    "layer_norm_eps": 1e-12,49    "length_penalty": 1.0,50    "max_length": 20,51    "max_position_embeddings": 512,52    "min_length": 0,53    "model_type": "bert",54    "no_repeat_ngram_size": 0,55    "num_attention_heads": 4,56    "num_beam_groups": 1,57    "num_beams": 1,58    "num_hidden_layers": 5,59    "num_return_sequences": 1,60    "output_attentions": false,61    "output_hidden_states": false,62    "output_scores": false,63    "pad_token_id": 0,64    "position_embedding_type": "absolute",65    "prefix": null,66    "problem_type": null,67    "pruned_heads": {},68    "remove_invalid_values": false,69    "repetition_penalty": 1.0,70    "return_dict": true,71    "return_dict_in_generate": false,72    "sep_token_id": null,73    "suppress_tokens": null,74    "task_specific_params": null,75    "temperature": 1.0,76    "tf_legacy_loss": false,77    "tie_encoder_decoder": false,78    "tie_word_embeddings": true,79    "tokenizer_class": null,80    "top_k": 50,81    "top_p": 1.0,82    "torch_dtype": "float32",83    "torchscript": false,84    "transformers_version": "4.28.0.dev0",85    "type_vocab_size": 16,86    "typical_p": 1.0,87    "use_bfloat16": false,88    "use_cache": true,89    "vocab_size": 112490  },91  "torch_dtype": "float32",92  "transformers_version": null,93  "vision_config": {94    "_name_or_path": "/tmp/tmphwq2c69y/encoder/ViTModel",95    "add_cross_attention": false,96    "architectures": [97      "ViTModel"98    ],99    "attention_probs_dropout_prob": 0.1,100    "bad_words_ids": null,101    "begin_suppress_tokens": null,102    "bos_token_id": null,103    "chunk_size_feed_forward": 0,104    "cross_attention_hidden_size": null,105    "decoder_start_token_id": null,106    "diversity_penalty": 0.0,107    "do_sample": false,108    "early_stopping": false,109    "encoder_no_repeat_ngram_size": 0,110    "encoder_stride": 2,111    "eos_token_id": null,112    "exponential_decay_length_penalty": null,113    "finetuning_task": null,114    "forced_bos_token_id": null,115    "forced_eos_token_id": null,116    "hidden_act": "gelu",117    "hidden_dropout_prob": 0.1,118    "hidden_size": 32,119    "id2label": {120      "0": "LABEL_0",121      "1": "LABEL_1"122    },123    "image_size": 30,124    "initializer_range": 0.02,125    "intermediate_size": 37,126    "is_decoder": false,127    "is_encoder_decoder": false,128    "label2id": {129      "LABEL_0": 0,130      "LABEL_1": 1131    },132    "layer_norm_eps": 1e-12,133    "length_penalty": 1.0,134    "max_length": 20,135    "min_length": 0,136    "model_type": "vit",137    "no_repeat_ngram_size": 0,138    "num_attention_heads": 4,139    "num_beam_groups": 1,140    "num_beams": 1,141    "num_channels": 3,142    "num_hidden_layers": 5,143    "num_return_sequences": 1,144    "output_attentions": false,145    "output_hidden_states": false,146    "output_scores": false,147    "pad_token_id": null,148    "patch_size": 2,149    "prefix": null,150    "problem_type": null,151    "pruned_heads": {},152    "qkv_bias": true,153    "remove_invalid_values": false,154    "repetition_penalty": 1.0,155    "return_dict": true,156    "return_dict_in_generate": false,157    "sep_token_id": null,158    "suppress_tokens": null,159    "task_specific_params": null,160    "temperature": 1.0,161    "tf_legacy_loss": false,162    "tie_encoder_decoder": false,163    "tie_word_embeddings": true,164    "tokenizer_class": null,165    "top_k": 50,166    "top_p": 1.0,167    "torch_dtype": "float32",168    "torchscript": false,169    "transformers_version": "4.28.0.dev0",170    "typical_p": 1.0,171    "use_bfloat16": false172  }173}174