423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-02 19:52:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix Llama model save for full param train

Browse Source 
Former-commit-id: eb178eaff390a1dc342cc35ab8c7820d654f3717
This commit is contained in:
marko1616 2024-03-30 23:45:04 +08:00
parent 3bf6dde3a5
commit 67c05c2031
2 changed files with 9 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
src/llmtuner/model/patcher.py
View File

@ -312,6 +312,15 @@ def patch_config(
def patch_model(
model: "PreTrainedModel", tokenizer: "PreTrainedTokenizer", model_args: "ModelArguments", is_trainable: bool
) -> None:
#Config check and fix
gen_config = model.generation_config
if not gen_config.do_sample and (
(gen_config.temperature is not None and gen_config.temperature != 1.0)
or (gen_config.top_p is not None and gen_config.top_p != 1.0)
or (gen_config.typical_p is not None and gen_config.typical_p != 1.0)
):
gen_config.do_sample = True
if "GenerationMixin" not in str(model.generate.__func__):
model.generate = MethodType(PreTrainedModel.generate, model)

8
src/llmtuner/train/tuner.py
View File

@ -64,14 +64,6 @@ def export_model(args: Optional[Dict[str, Any]] = None):
for param in model.parameters():
param.data = param.data.to(output_dtype)
gen_config = model.generation_config # check and fix generation config
if not gen_config.do_sample and (
(gen_config.temperature is not None and gen_config.temperature != 1.0)
or (gen_config.top_p is not None and gen_config.top_p != 1.0)
or (gen_config.typical_p is not None and gen_config.typical_p != 1.0)
):
gen_config.do_sample = True
model.save_pretrained(
save_directory=model_args.export_dir,
max_shard_size="{}GB".format(model_args.export_size),