microsoft / microsoft/MInference
[Question]: can TriMix be used in large models, such as deepseek, qwen3-235b?
Open
Nobody has claimed this yet.
question
- Dominant language
- Python
- Stars
- 1.2k
- Forks
- 82
- Avg merge
- 1d 18h
- Merged PRs (30d)
- 1
Description
Describe the issue
I tried to use Trimix on qwen-235b, with different params such as starting layer=48, but still get an unrecognizable output, i.e messy code
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 by reproducing TriMix with qwen-235b using the reported starting layer=48 and the other parameter variants. Check the repository's TriMix entry point and model-support guidance, then establish whether recognizable output can be produced or whether the model is unsupported; the issue does not name a file or test.
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
- 20/100