{ "_name_or_path": "Sheared-Llama3-3456h-4kv-8192mlp", "architectures": [ "LlamaForCausalLM" ], "bos_token_id": 1, "eos_token_id": 2, "head_dim": 128, "hidden_act": "silu", "hidden_size": 3456, "initializer_range": 0.02, "intermediate_size": 8192, "max_position_embeddings": 2048, "model_type": "llama", "num_attention_heads": 16, "num_hidden_layers": 32, "num_key_value_heads": 4, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 500000, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.33.0", "use_cache": true, "vocab_size": 128256 }