423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-29 02:00:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

[model] switch to gptqmodel (#8108)

Browse Source
This commit is contained in:
hoshi-hiyouga
2025-05-19 22:25:40 +08:00
committed by GitHub
parent bc7f00f2c7
commit 45030ff803
9 changed files with 78 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/llamafactory/model/patcher.py
View File

@@ -102,8 +102,8 @@ def patch_config(
else:
model_args.compute_dtype = infer_optim_dtype(model_dtype=getattr(config, "torch_dtype", None))
configure_attn_implementation(config, model_args, is_trainable)
configure_rope(config, model_args, is_trainable)
configure_attn_implementation(config, model_args)
configure_rope(config, model_args)
configure_longlora(config, model_args, is_trainable)
configure_quantization(config, tokenizer, model_args, init_kwargs)
configure_moe(config, model_args, is_trainable)