ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix #1659

Browse Source 
Former-commit-id: e4123129aae59f4123d53c1f5320e3d5e09ae26d
This commit is contained in:
hiyouga
2023-11-28 20:52:28 +08:00
parent 569860d7ac
commit 670ee3934f
4 changed files with 12 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/llmtuner/train/tuner.py
View File

@@ -38,8 +38,8 @@ def export_model(args: Optional[Dict[str, Any]] = None):
model_args, _, finetuning_args, _ = get_infer_args(args)
model, tokenizer = load_model_and_tokenizer(model_args, finetuning_args)
if getattr(model, "quantization_method", None) == "gptq":
raise ValueError("Cannot export a GPTQ quantized model.")
if getattr(model, "quantization_method", None) in ["gptq", "awq"]:
raise ValueError("Cannot export a GPTQ or AWQ quantized model.")
model.config.use_cache = True
model.save_pretrained(finetuning_args.export_dir, max_shard_size="{}GB".format(finetuning_args.export_size))