nm-testing/Qwen3-VL-8B-Instruct-W4A16
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: nm-testing/Qwen3-VL-8B-Instruct-W4A16
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-08 10:15:13 +08:00
commit 9bc7f6fa4e
18 changed files with 2115 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
recipe.yaml Normal file
View File

@@ -0,0 +1,10 @@
default_stage:
default_modifiers:
GPTQModifier:
targets: [Linear]
ignore: ['re:.*lm_head', 're:visual.*', 're:model.visual.*', 're:.*mlp.gate$']
scheme: W4A16
block_size: 128
dampening_frac: 0.01
actorder: static
offload_hessians: false