leehanchung / SMILE-factory
Finetune Falcon, LLaMA, MPT, and RedPajama on consumer hardware using PEFT LoRA
Why this job: says: finetune, lora; topics: lora
What it does
A playground for artificial / synthetic data. In *One Piece*, the SMILE Factory mass-produces *artificial* Devil Fruits — synthetic stand-ins for natural powers, churned out by the vat-load from SAD. SMILE-factory is the analog: one factory for manufacturing synthetic data to push AI further — generate tasks, run them through agents, score the trajectories, feed the signal back into training. Raw questions in, model capability out.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 51 days ago
- Stars
- 106
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 92% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 20% closed
- 8 still open
- Pull requests
- 87 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 |
|---|---|---|---|---|
| hiyouga / LlamaFactory | 75,952 | today | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 92%
- Jupyter Notebook 4%
- Makefile 2%
- Shell 1%
Topics
- agi
- falcon
- gpt
- llama
- llm
- lora
- mpt
- nlp
- redpajama
Project record
- JobFine-tuning
- StatusListed
- Commits151
- Forks16
- Watching2
- Stars in 28 days0
- CreatedMay 7, 2023
- First seen by usNov 7, 2026
- CheckedNov 7, 2026