{ "_name_or_path": "/tmp/tmp5wtl9eyu", "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 32013, "eos_token_id": 32014, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 5504, "max_position_embeddings": 16384, "model_type": "llama", "num_attention_heads": 16, "num_hidden_layers": 24, "num_key_value_heads": 16, "pretraining_tp": 1, "quantization_config": { "bnb_4bit_compute_dtype": "bfloat16", "bnb_4bit_quant_type": "fp4", "bnb_4bit_use_double_quant": true, "llm_int8_enable_fp32_cpu_offload": false, "llm_int8_has_fp16_weight": false, "llm_int8_skip_modules": [ "lm_head" ], "llm_int8_threshold": 6.0, "load_in_4bit": false, "load_in_8bit": true, "quant_method": "bitsandbytes" }, "rms_norm_eps": 1e-06, "rope_scaling": { "factor": 4.0, "type": "linear" }, "rope_theta": 100000, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.37.1", "use_cache": true, "vocab_size": 32256 }