huggingface / huggingface/alignment-handbook
"RuntimeError: The size of tensor a (0) must match the size of tensor b (4096) at non-singleton dimension 1" (DPO + LoRA)
Open
bug
- Dominant language
- Python
- Stars
- 5.7k
- Forks
- 490
- Avg merge
- 2m
- Merged PRs (30d)
- 1
Description
So I'm attempting to run the DPO LoRA script and I'm getting this error:
```
RuntimeError: The size of tensor a (0) must match the size of tensor b (4096) at non-singleton dimension 1
```
... when the `model.merge_and_load()` runs here:
```
base_model = AutoModelForCausalLM.from_pretrained(peft_config.base_model_name_or_path, **model_kwargs)
model = PeftModel.from_pretrained(base_model, model_args.model_name_or_path, revision=model_args.model_revision)
model.eval()
model = model.merge_and_unload()
```
Any ideas?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.