shibing624 / MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。
Why this job: says: rlhf
What it does
Supervised Finetuning, RLHF(Reward Modeling and Reinforcement Learning), DPO(Direct Preference Optimization) and standalone OPD(On-Policy Distillation).
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 55 days ago
- Stars
- 5,888
- +10 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- 2.7.0
- Released 6 months ago
- Built with
- Python
- 84% of the code
Is it looked after?
- Contributors
- 3
- Last 90 days
- Issues
- 99% closed
- 6 still open
- Pull requests
- 34 merged
- 0 waiting
- Releases
- 17
- 3 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| oumi-ai / oumi | 9,429 | 3 days ago | Apache-2.0 | No downloads |
| h2oai / h2o-llmstudio | 5,194 | 2 days ago | Apache-2.0 | No downloads |
| Enping-Hu / minimind-deep-dive | 217 | 19 days ago | CC-BY-4.0 | No downloads |
More: languages, topics and project record
Languages
- Python 84%
- Jupyter Notebook 13%
- Shell 3%
Topics
- llama
- chatgpt
- gpt
- llm
- medical
- dpo
- medicalgpt
Project record
- JobFine-tuning
- StatusListed
- Commits672
- Forks804
- Watching39
- Stars in 28 days+41
- CreatedJun 2, 2023
- First seen by usNov 7, 2026
- CheckedNov 9, 2026