{ "_name_or_path": "meta-llama/Llama-2-70b-hf", "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 28672, "max_position_embeddings": 4096, "model_type": "llama", "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "pretraining_tp": 1, "quantization_config": { "batch_size": 1, "bits": 4, "block_name_to_quantize": null, "cache_block_outputs": true, "damp_percent": 0.1, "dataset": "c4", "desc_act": false, "exllama_config": { "version": 1 }, "group_size": 128, "max_input_length": null, "model_seqlen": null, "module_name_preceding_first_block": null, "modules_in_block_to_quantize": null, "pad_token_id": null, "quant_method": "gptq", "sym": true, "tokenizer": null, "true_sequential": true, "use_cuda_fp16": false, "use_exllama": true }, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.37.0.dev0", "use_cache": true, "vocab_size": 32000 }