{ "architectures": [ "LLMEncoder" ], "auto_map": { "AutoConfig": "llmencoder.LLMEncoderConfig", "AutoModel": "llmencoder.LLMEncoder" }, "base_model": "microsoft/Phi-3-mini-4k-instruct", "doc_max_length": 400, "model_config": { "_name_or_path": "microsoft/Phi-3-mini-4k-instruct", "add_cross_attention": false, "architectures": [ "Phi3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config", "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM" }, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 1, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "diversity_penalty": 0.0, "do_sample": false, "early_stopping": false, "embd_pdrop": 0.0, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 32000, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "silu", "hidden_size": 3072, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 8192, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 4096, "min_length": 0, "model_type": "phi3", "no_repeat_ngram_size": 0, "num_attention_heads": 32, "num_beam_groups": 1, "num_beams": 1, "num_hidden_layers": 25, "num_key_value_heads": 32, "num_return_sequences": 1, "original_max_position_embeddings": 4096, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 32000, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "resid_pdrop": 0.0, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "sep_token_id": null, "sliding_window": 2047, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": "bfloat16", "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "vocab_size": 32064 }, "pooling_mode": "weighted_mean", "skip_instruction": true, "torch_dtype": "bfloat16", "transformers_version": "4.44.2" }