| { |
| "architectures": [ |
| "LlamaForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 0, |
| "eos_token_id": 0, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "initializer_range": 0.02, |
| "intermediate_size": 8192, |
| "max_position_embeddings": 2048, |
| "mlp_bias": false, |
| "model_type": "llama", |
| "num_attention_heads": 32, |
| "num_hidden_layers": 24, |
| "num_key_value_heads": 32, |
| "pretraining_tp": 1, |
| "quantization_config": { |
| "bits": 3, |
| "checkpoint_format": "gptq", |
| "desc_act": true, |
| "group_size": 128, |
| "lm_head": false, |
| "meta": { |
| "damp_auto_increment": 0.01, |
| "damp_percent": 0.01, |
| "mse": 0.0, |
| "quantizer": [ |
| "gptqmodel:4.0.0-dev" |
| ], |
| "static_groups": false, |
| "true_sequential": true, |
| "uri": "https://github.com/modelcloud/gptqmodel", |
| "v2": false, |
| "v2_alpha": 0.25 |
| }, |
| "pack_dtype": "int32", |
| "quant_method": "gptq", |
| "sym": true |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 10000.0, |
| "tie_word_embeddings": true, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.52.2", |
| "use_cache": true, |
| "vocab_size": 49152 |
| } |
|
|
