gpu/generate.py error
Open
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 40.3k
- Forks
- 3.7k
- PR merge metrics
- No merged PRs in 30d
Description
torch.cuda.synchronize()
stats.phase("decode" if use_cuda_graphs else "total")
eos_id = self.tokenizer.eot_id
error：
AttributeError: 'Tokenizer' object has no attribute 'eot_id'. Did you mean: 'eos_id'?
is code wrong? should it be
eos_id = self.tokenizer.eos_id?
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start in gpu/generate.py at the tokenizer assignment shown in the issue. Confirm whether Tokenizer exposes eos_id rather than eot_id, then run the relevant generation path to verify the AttributeError is gone and end-of-sequence handling works.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 1/5
- Estimated time
- Under an hour
- Activity status
- Stale
- Clarity
- Clearly specified
- Newbie friendliness
- 48/100