初始化项目,由ModelHub XC社区提供模型
Model: JongYeop/Qwen2.5-14B-Instruct-FP4-W4A4 Source: Original Platform
This commit is contained in:
6
recipe.yaml
Normal file
6
recipe.yaml
Normal file
@@ -0,0 +1,6 @@
|
||||
quant_stage:
|
||||
quant_modifiers:
|
||||
QuantizationModifier:
|
||||
targets: [Linear]
|
||||
ignore: [lm_head]
|
||||
scheme: NVFP4
|
||||
Reference in New Issue
Block a user