| {"architectures": ["LlamaForCausalLM"], "auto_map": {"AutoModelForCausalLM":"modeling_llama.LlamaForCausalLM"},"model_type": "llama", "vocab_size": 160896, "bos_token_id": 1, "eos_token_id": 2, "pad_token_id": 0, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "num_attention_heads": 32, "num_key_value_heads": 8, "num_hidden_layers": 32, "rms_norm_eps": 1e-05, "rotary_percent": 1.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": true, "transformers_version": "4.33.1", "rope_theta": 500000} |