truthseek / model_architecture.json
annalhq's picture
chore: upload
d4458e5 verified
"{\"class_name\": \"TFBertForSequenceClassification\", \"config\": {\"return_dict\": true, \"output_hidden_states\": false, \"output_attentions\": false, \"torchscript\": false, \"torch_dtype\": null, \"use_bfloat16\": false, \"tf_legacy_loss\": false, \"pruned_heads\": {}, \"tie_word_embeddings\": true, \"chunk_size_feed_forward\": 0, \"is_encoder_decoder\": false, \"is_decoder\": false, \"cross_attention_hidden_size\": null, \"add_cross_attention\": false, \"tie_encoder_decoder\": false, \"max_length\": 20, \"min_length\": 0, \"do_sample\": false, \"early_stopping\": false, \"num_beams\": 1, \"num_beam_groups\": 1, \"diversity_penalty\": 0.0, \"temperature\": 1.0, \"top_k\": 50, \"top_p\": 1.0, \"typical_p\": 1.0, \"repetition_penalty\": 1.0, \"length_penalty\": 1.0, \"no_repeat_ngram_size\": 0, \"encoder_no_repeat_ngram_size\": 0, \"bad_words_ids\": null, \"num_return_sequences\": 1, \"output_scores\": false, \"return_dict_in_generate\": false, \"forced_bos_token_id\": null, \"forced_eos_token_id\": null, \"remove_invalid_values\": false, \"exponential_decay_length_penalty\": null, \"suppress_tokens\": null, \"begin_suppress_tokens\": null, \"architectures\": [\"BertForMaskedLM\"], \"finetuning_task\": null, \"id2label\": {\"0\": \"LABEL_0\", \"1\": \"LABEL_1\"}, \"label2id\": {\"LABEL_0\": 0, \"LABEL_1\": 1}, \"tokenizer_class\": null, \"prefix\": null, \"bos_token_id\": null, \"pad_token_id\": 0, \"eos_token_id\": null, \"sep_token_id\": null, \"decoder_start_token_id\": null, \"task_specific_params\": null, \"problem_type\": null, \"_name_or_path\": \"bert-base-uncased\", \"_attn_implementation_autoset\": false, \"transformers_version\": \"4.48.3\", \"gradient_checkpointing\": false, \"model_type\": \"bert\", \"vocab_size\": 30522, \"hidden_size\": 768, \"num_hidden_layers\": 12, \"num_attention_heads\": 12, \"hidden_act\": \"gelu\", \"intermediate_size\": 3072, \"hidden_dropout_prob\": 0.1, \"attention_probs_dropout_prob\": 0.1, \"max_position_embeddings\": 512, \"type_vocab_size\": 2, \"initializer_range\": 0.02, \"layer_norm_eps\": 1e-12, \"position_embedding_type\": \"absolute\", \"use_cache\": true, \"classifier_dropout\": null}, \"keras_version\": \"2.18.0\", \"backend\": \"tensorflow\"}"