{ "_name_or_path": "neuralmagic/Llama-2-7b-pruned70-retrained-evolcodealpaca-quant-ds", "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 4096, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "tokenizer_class": "LlamaTokenizerFast", "torch_dtype": "float16", "transformers_version": "1.7.0.20240504", "use_cache": true, "vocab_size": 32000 }