| { | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 14336, | |
| "max_position_embeddings": 32768, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 500000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float16", | |
| "vocab_size": 129024, | |
| "quantization_config": { | |
| "quant_method": "exl2", | |
| "version": "0.2.8", | |
| "bits": 8.0, | |
| "head_bits": 8, | |
| "calibration": { | |
| "rows": 115, | |
| "length": 2048, | |
| "dataset": "(default)" | |
| } | |
| } | |
| } |