OptimalScale / OptimalScale/LMFlow
[BUG] Cannot run the raft_align with model Qwen2.5
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 8.5k
- Forks
- 822
- PR merge metrics
- No merged PRs in 30d
Description
Describe the bug
Run raft align on Qwen2.5 and meet error
File "LMFlow/src/lmflow/pipeline/auto_pipeline.py", line 68, in get_pipeline
[rank5]: raise NotImplementedError(
[rank5]: NotImplementedError: Please install the necessary dependencies to use pipeline "raft_aligner"
When I tried to downgrade the transformers<4.35.0, Qwen2Tokenizer is not yet defined.
I meet error
Tokenizer class Qwen2Tokenizer does not exist or is not currently imported
Contributor guide
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 LMFlow/src/lmflow/pipeline/auto_pipeline.py at line 68 and reproduce raft_align with Qwen2.5. Investigate the dependency error and the Qwen2Tokenizer failure after downgrading transformers; done means the raft_aligner runs with Qwen2.5 without either error.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100