MagiSeek-Pro-V1-AutoRound-W4A16-Tuning/quantization_config.json at main - MagiSeek-Pro-V1-AutoRound-W4A16-Tuning - Gitea: Git with a cup of tea

LeaderboardModel1/MagiSeek-Pro-V1-AutoRound-W4A16-Tuning

Files

ModelHub XC c506dd7794 初始化项目，由ModelHub XC社区提供模型

Model: LeaderboardModel1/MagiSeek-Pro-V1-AutoRound-W4A16-Tuning
Source: Original Platform

2026-08-12 02:45:16 +08:00

11 lines

255 B

JSON

Raw Permalink Blame History

 {
   "bits": 4,
   "data_type": "int",
   "group_size": 128,
   "sym": true,
   "low_gpu_mem_usage": true,
   "autoround_version": "0.14.2",
   "block_name_to_quantize": "model.layers",
   "quant_method": "auto-round",
   "packing_format": "auto_round:auto_gptq"
 }