Downloads · 30 days
7
11% of all-time downloads
mistral-7b-medical-instruct
AbhijithSK/mistral-7b-medical-instruct
mistral-7b-medical-instruct is a machine learning model from AbhijithSK. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as apache-2.0.
Fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on medical Q&A data using QLoRA.
All-time downloads
64
Public
Repo size
301 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt164 MB · 52%
At a glance
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Jun 19, 2026
- Updated
- Jun 19, 2026
- SHA
- cf213a0a
Base models
Model card
From the Hugging Face model README
Mistral-7B Medical Instruct (QLoRA Fine-tuned)
Fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on medical Q&A data using QLoRA.
Training Results
| Metric | Value |
|---|---|
| Final Train Loss | 0.022 |
| Token Accuracy | 98.9% |
| Epochs | 3 |
| Training Time | ~2h 50min on T4 GPU |
| Trainable Params | 13.6M / 7.25B (0.19%) |
Method
- Base model: mistralai/Mistral-7B-Instruct-v0.2
- Dataset: medalpaca/medical_meadow_pubmed_causal (2,446 samples)
- Quantization: 4-bit NF4 (QLoRA)
- LoRA rank: 16, alpha: 32
- Target modules: q_proj, v_proj, k_proj, o_proj
Usage
from peft import PeftModel from transformers import AutoModelForCausalLM, AutoTokenizer
base = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2") model = PeftModel.from_pretrained(base, "AbhijithSK/mistral-7b-medical-instruct") tokenizer = AutoTokenizer.from_pretrained("AbhijithSK/mistral-7b-medical-instruct")
Limitations
For research only. Not for clinical use. Always consult a qualified physician.
Author
Abhijith SK - GitHub: https://github.com/AbhijithSK
- Library
- peft
- License
- apache-2.0
- Languages
- en
- Created
- Jun 19, 2026
- Updated
- Jun 19, 2026