423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-10-15 08:08:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

tiny fix

Browse Source 
Former-commit-id: 3b6e1132c4d203e6d5376cf97e81cc160697c822
This commit is contained in:
hiyouga 2024-02-29 17:28:50 +08:00
parent 48d2e6d7fe
commit 30855b924a
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
src/llmtuner/model/patcher.py
View File

@ -169,11 +169,14 @@ def _configure_quantization(
quantization_config["use_exllama"] = False # disable exllama quantization_config["use_exllama"] = False # disable exllama
if quantization_config.get("quant_method", None) == "aqlm": if quantization_config.get("quant_method", None) == "aqlm":
require_version(
"transformers>=4.39.0.dev0", "To fix: pip install git+https://github.com/huggingface/transformers.git"
)
quantization_config["bits"] = 2 quantization_config["bits"] = 2
logger.info( logger.info(
"Loading {}-bit {}-quantized model.".format( "Loading {}-bit {}-quantized model.".format(
quantization_config.get("bits", "?"), quantization_config.get("quant_method", None) quantization_config.get("bits", "?"), str(quantization_config.get("quant_method", "")).upper()
) )
) )