{ "_name_or_path": "../trained_model/EXAONE-3.0-7.8B-Instruct-translation-general12m-en-ko-e1-b64-trc1400k-e1-b64-trc_uniform_313k_eval_45_filtered_chat-e2-b8-lr1e-05-packTrue-8192/checkpoint-578", "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 361, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pad_token_id": 0, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.44.1", "use_cache": true, "vocab_size": 102400 }