| { | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoModelForCausalLM": "modeling_flash_llama.LlamaForCausalLM" | |
| }, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 13824, | |
| "max_position_embeddings": 8192, | |
| "model_type": "llama", | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 40, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 2.0, | |
| "type": "linear" | |
| }, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.33.0", | |
| "use_cache": true, | |
| "vocab_size": 32000, | |
| "pad_token_id": 0, | |
| "quantization_config": { | |
| "bits": 4, | |
| "group_size": 128, | |
| "damp_percent": 0.1, | |
| "desc_act": true, | |
| "sym": true, | |
| "true_sequential": true, | |
| "model_name_or_path": null, | |
| "model_file_base_name": "model", | |
| "quant_method": "gptq" | |
| } | |
| } |