| { |
| "architectures": [ |
| "MistralForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "bos_token_id": 1, |
| "eos_token_id": 2, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 6144, |
| "initializer_range": 0.02, |
| "intermediate_size": 16384, |
| "max_position_embeddings": 32768, |
| "model_type": "mistral", |
| "num_attention_heads": 48, |
| "num_hidden_layers": 56, |
| "num_key_value_heads": 8, |
| "quantization_config": { |
| "bits": 3, |
| "checkpoint_format": "gptq", |
| "desc_act": true, |
| "group_size": 128, |
| "lm_head": false, |
| "meta": { |
| "damp_auto_increment": 0.0025, |
| "damp_percent": 0.01, |
| "mse": 0.0, |
| "quantizer": [ |
| "gptqmodel:2.2.0" |
| ], |
| "static_groups": false, |
| "true_sequential": true, |
| "uri": "https://github.com/modelcloud/gptqmodel" |
| }, |
| "pack_dtype": "int32", |
| "quant_method": "gptq", |
| "sym": true |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_theta": 1000000.0, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.51.3", |
| "use_cache": true, |
| "vocab_size": 32768 |
| } |
|
|
