neuralmagic/Llama-3.2-1B-Instruct-FP8
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: neuralmagic/Llama-3.2-1B-Instruct-FP8
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-24 21:11:13 +08:00
commit 4a247901b5
10 changed files with 413101 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
recipe.yaml Normal file
View File

@@ -0,0 +1,7 @@
quant_stage:
quant_modifiers:
QuantizationModifier:
ignore: [lm_head]
scheme: FP8
observer: mse
targets: [Linear]