| { | |
| "architectures": [ | |
| "LLaMAForCausalLM" | |
| ], | |
| "bos_token_id": 0, | |
| "eos_token_id": 1, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "intermediate_size": 11008, | |
| "initializer_range": 0.02, | |
| "max_sequence_length": 2048, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "pad_token_id": 32000, | |
| "rms_norm_eps": 1e-06, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.27.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 32001, | |
| "pretraining_tp": 1, | |
| "quantization_config": { | |
| "quant_method": "awq", | |
| "zero_point": true, | |
| "group_size": 128, | |
| "bits": 4, | |
| "version": "gemm" | |
| } | |
| } |