| { |
| "architectures": [ |
| "LlamaForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 128000, |
| "dtype": "bfloat16", |
| "eos_token_id": [ |
| 128001, |
| 128008, |
| 128009 |
| ], |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 3072, |
| "initializer_range": 0.02, |
| "intermediate_size": 8192, |
| "max_position_embeddings": 131072, |
| "mlp_bias": false, |
| "model_type": "llama", |
| "num_attention_heads": 24, |
| "num_hidden_layers": 28, |
| "num_key_value_heads": 8, |
| "pad_token_id": 128009, |
| "pretraining_tp": 1, |
| "quantization_config": { |
| "bits": 4, |
| "checkpoint_format": "gptq", |
| "desc_act": false, |
| "format": "gptq", |
| "group_size": 128, |
| "lm_head": false, |
| "meta": { |
| "act_group_aware": true, |
| "auto_forward_data_parallel": true, |
| "damp_auto_increment": 0.01, |
| "damp_percent": 0.05, |
| "failsafe": { |
| "smooth": null, |
| "strategy": "rtn", |
| "threshold": "0.5%" |
| }, |
| "gc_mode": "interval", |
| "gptaq": null, |
| "hessian": { |
| "chunk_bytes": null, |
| "chunk_size": null, |
| "staging_dtype": "float32" |
| }, |
| "mock_quantization": false, |
| "mse": 0.0, |
| "offload_to_disk": true, |
| "offload_to_disk_path": "./gptqmodel_offload/exjcistq-hxydtqju/", |
| "pack_impl": "cpu", |
| "quantizer": [ |
| "gptqmodel:5.8.0" |
| ], |
| "static_groups": false, |
| "true_sequential": true, |
| "uri": "https://github.com/modelcloud/gptqmodel", |
| "vram_strategy": "exclusive", |
| "wait_for_submodule_finalizers": false |
| }, |
| "pack_dtype": "int32", |
| "quant_method": "gptq", |
| "sym": true |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_parameters": { |
| "factor": 32.0, |
| "high_freq_factor": 4.0, |
| "low_freq_factor": 1.0, |
| "original_max_position_embeddings": 8192, |
| "rope_theta": 500000.0, |
| "rope_type": "llama3" |
| }, |
| "tie_word_embeddings": true, |
| "transformers_version": "5.2.0", |
| "use_cache": true, |
| "vocab_size": 128256 |
| } |
|
|
