MetaMath-NeuralHermes-2.5-Mistral-7B-Linear-GPTQ/quantize_config.json at main - MetaMath-NeuralHermes-2.5-Mistral-7B-Linear-GPTQ - Gitea: Git with a cup of tea

TheBloke/MetaMath-NeuralHermes-2.5-Mistral-7B-Linear-GPTQ

Files

ModelHub XC c2897f7d30 初始化项目，由ModelHub XC社区提供模型

Model: TheBloke/MetaMath-NeuralHermes-2.5-Mistral-7B-Linear-GPTQ
Source: Original Platform

2026-08-10 13:30:13 +08:00

11 lines

212 B

JSON

Raw Permalink Blame History

 {
   "bits": 4,
   "group_size": 128,
   "damp_percent": 0.1,
   "desc_act": true,
   "static_groups": false,
   "sym": true,
   "true_sequential": true,
   "model_name_or_path": null,
   "model_file_base_name": "model"
 }