| { | |
| "_name_or_path": "/fsx/llama405b/instruct", | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "eos_token_id": [ | |
| 128001, | |
| 128008, | |
| 128009 | |
| ], | |
| "hidden_act": "silu", | |
| "hidden_size": 16384, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 53248, | |
| "max_position_embeddings": 16384, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 128, | |
| "num_hidden_layers": 126, | |
| "num_key_value_heads": 16, | |
| "pretraining_tp": 1, | |
| "quantization_config": { | |
| "bits": 4, | |
| "damp_percent": 0.1, | |
| "desc_act": true, | |
| "group_size": 128, | |
| "is_marlin_format": false, | |
| "model_file_base_name": "gptq_model-4bit-128g", | |
| "model_name_or_path": "/fsx/llama405b/4bit-gptq-instruct", | |
| "quant_method": "gptq", | |
| "static_groups": false, | |
| "sym": true, | |
| "true_sequential": true | |
| }, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 8.0, | |
| "low_freq_factor": 1.0, | |
| "high_freq_factor": 4.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| }, | |
| "rope_theta": 500000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.42.4", | |
| "use_cache": true, | |
| "vocab_size": 128256 | |
| } | |