#129 · Primary category： Foundation Models
medAlpaca
LLM finetuned for medical question answering
Project last updated：09/07/23
GitHub Stars
564
Forks
73
Contributors
6
License
GPL-3.0
Why we included this project
medAlpaca is a practical starting point for teams that want a medical question-answering model without training one from scratch. It ships LLaMA-based models fine-tuned on biomedical sources like flashcards, wikis, USMLE self-assessments, and medical dialogue data, along with the training scripts and memory benchmarks needed to reproduce or extend them. The LoRA and 8-bit training paths are especially useful if you plan to adapt the approach to your own clinical or educational text on a single GPU. Researchers and developers prototyping medical chatbots will find both ready weights and a clear recipe for domain fine-tuning in one place, plus the Medical Meadow dataset collection used to build it.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
transformers
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
MiniCPM-V
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
generative-models
Generative Models by Stability AI
unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities