423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-11-05 18:32:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix #3365

Browse Source 
Former-commit-id: 415ce41e8fa887e980e5bd575c8e95bd4076b90b
This commit is contained in:
hiyouga 2024-04-21 19:20:18 +08:00
parent b353a080cb
commit 04da91e84e
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/llmtuner/model/patcher.py
View File

@ -139,6 +139,7 @@ def _configure_quantization(
if quant_method == QuantizationMethod.GPTQ: if quant_method == QuantizationMethod.GPTQ:
require_version("auto_gptq>=0.5.0", "To fix: pip install auto_gptq>=0.5.0") require_version("auto_gptq>=0.5.0", "To fix: pip install auto_gptq>=0.5.0")
quantization_config.pop("disable_exllama", None) # remove deprecated args
quantization_config["use_exllama"] = False # disable exllama quantization_config["use_exllama"] = False # disable exllama
if quant_method == QuantizationMethod.AWQ: if quant_method == QuantizationMethod.AWQ: