{ "_attn_implementation_autoset": true, "_name_or_path": "output/sft_llama3_3b/", "architectures": [ "LlamaForScore" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "do_normalize": false, "eos_token_id": 128001, "head_dim": 128, "hidden_act": "silu", "hidden_size": 3072, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 131072, "mean": [ 0.10040677338838577 ], "mlp_bias": false, "model_type": "llama", "momentum": 0.9, "normalizer_type": "ExponentialMovingAverage", "num_attention_heads": 24, "num_hidden_layers": 28, "num_key_value_heads": 8, "pad_token_id": 128256, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": { "factor": 32.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3" }, "rope_theta": 500000.0, "score_bias": true, "score_dim": 1, "score_type": "reward", "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.49.0", "use_cache": true, "var": [ 19.961563110351562 ], "vocab_size": 128258 }