Zihao-Wu06 / distillops
Black-box LLM distillation for any verifiable task, with text or image inputs: teacher API -> rejection sampling -> SFT -> eval -> GRPO
Why this job: says: distillation; topics: fine-tuning, reinforcement-learning, distillation
What it does
- Any verifiable task, one class. Teacher calls, rejection sampling, SFT, evaluation and GRPO are
- Any student model. Any causal LM from the Hugging Face hub or a local path can be the student
- Verified data, measured value. Teacher outputs are kept only if they pass your verifier (failed
- RL that tells you when it will not work. Before GRPO, the share of prompts that carry a learning
- Runs on the GPU you have. Precision is chosen from the hardware, batch sizes from free memory and
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 7 days ago
- Stars
- 101
- +78 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- None
- No issues filed
- Pull requests
- 6 merged
- 1 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| modelscope / ms-swift | 16,081 | yesterday | Apache-2.0 | No downloads |
| oumi-ai / oumi | 9,431 | 2 days ago | Apache-2.0 | No downloads |
| adithya-s-k / FineEnvs | 558 | 14 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 100%
Topics
- distillation
- fine-tuning
- grpo
- knowledge-distillation
- llm
- qwen
- reinforcement-learning
- rlvr
- sft
- small-language-models
- trl
- vllm
Project record
- JobFine-tuning
- StatusNew to our list
- Commits45
- Forks1
- Watching2
- CreatedOct 28, 2026
- First seen by usNov 11, 2026
- CheckedNov 11, 2026