#3131st of 41 in Training and fine-tuningFor science, health and research
medicalgpt
Training scripts for medical LLMs: pretraining, SFT, RLHF, DPO, GRPO
- Stars
- 5.9k
- License
- Apache-2.0
- Last commit
- Sep 2026
- Last release
- Apr 2026
- Language
- Python
5,097 on 3 Apr 20265,877 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
MedicalGPT is a set of Python scripts that train domain LLMs through continued pretraining, supervised fine-tuning, reward modeling with PPO/RLOO, DPO, ORPO, GRPO and on-policy distillation. It supports Qwen, Llama-3, Mixtral and other model families, with LoRA/QLoRA and DeepSpeed ZeRO configs. Gradio, FastAPI and OpenAI-style demo servers are included for inference.
Who it is for: Engineers fine-tuning open LLMs on domain data with LoRA or full-parameter runs
Strengths
- Covers PT, SFT, RM, PPO, DPO, ORPO, GRPO and OPD in one repo with shell launchers
- Ships DeepSpeed ZeRO-1/2/3 configs and a VRAM table (QLoRA 4-bit 7B about 6GB)
- Supports tool-call fine-tuning via SFT and DPO using ShareGPT-format jsonl
- Colab notebooks run full PT+SFT+DPO or PPO pipelines in roughly 15-20 minutes
Weaknesses
- Script collection, not a packaged library or UI; you edit shell scripts and arguments
- Stages are chained by hand, merging LoRA adapters between each one
- README is mostly Chinese; the English version is a separate file
- No Docker or compose files; setup is pip install -r requirements.txt
What it needs
- GPU required
- Needs PyTorch, Hugging Face Transformers, PEFT, DeepSpeed
- Models: Qwen 2/2.5/3.5, Llama-3, Mixtral 8x7B, Baichuan, ChatGLM
Quick answers
Is medicalgpt open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Does medicalgpt need a GPU?
Yes, it needs a GPU.
Also in Training and fine-tuning
See all 41| Rank | Project | Score |
|---|---|---|
| 1 | unslothDesktop and web app to run and fine-tune local models | 88 out of 100 |
| 2 | peftPython library for LoRA and other parameter-efficient fine-tuning of Transformers models | 86 out of 100 |
| 3 | deepspeedPyTorch library for distributed training of very large models with ZeRO | 85 out of 100 |
| #4 | verlReinforcement learning training library for LLM post-training with PPO and GRPO | 84 out of 100 |
| #5 | trlPost-training library with SFT, DPO, GRPO and KTO trainers | 83 out of 100 |