LeaderboardModel1/MagiSeek-Pro-V1-AutoRound-W4A16-Tuning
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: LeaderboardModel1/MagiSeek-Pro-V1-AutoRound-W4A16-Tuning
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-12 02:45:16 +08:00
commit c506dd7794
12 changed files with 1285 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
quantization_config.json Normal file
View File

@@ -0,0 +1,11 @@
{
"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"
}