| { | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 128000, | |
| "eos_token_id": [ | |
| 128001, | |
| 128008, | |
| 128009 | |
| ], | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 16, | |
| "num_key_value_heads": 8, | |
| "pretraining_tp": 1, | |
| "quantization_config": { | |
| "algo_config": null, | |
| "exclude": [], | |
| "export": { | |
| "kv_cache_group": [], | |
| "min_kv_scale": 0.0, | |
| "pack_method": "reorder", | |
| "weight_format": "real_quantized", | |
| "weight_merge_groups": null | |
| }, | |
| "global_quant_config": { | |
| "bias": null, | |
| "input_tensors": null, | |
| "output_tensors": null, | |
| "target_device": null, | |
| "weight": { | |
| "ch_axis": 1, | |
| "dtype": "uint4", | |
| "group_size": 128, | |
| "is_dynamic": false, | |
| "observer_cls": "PerGroupMinMaxObserver", | |
| "qscheme": "per_group", | |
| "round_method": "half_even", | |
| "scale_type": "float", | |
| "symmetric": false | |
| } | |
| }, | |
| "layer_quant_config": {}, | |
| "layer_type_quant_config": {}, | |
| "quant_method": "quark", | |
| "quant_mode": "eager_mode", | |
| "softmax_quant_spec": null | |
| }, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 32.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| }, | |
| "rope_theta": 500000.0, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.50.3", | |
| "use_cache": true, | |
| "vocab_size": 128256 | |
| } | |