dakshjain-1616/gemma-3-12b-medical-sft

Fine-tunes google/gemma-3-12b-it with Unsloth SFT and LoRA (r=32, alpha=64) on 1000 synthetic medical reasoning samples — symptom triage, differential diagnosis, drug interaction checks. Response-Only Training with Gemma-3 chat format and block masking. Exports GGUF Q4_K_M (~7.8GB) for 16GB RAM CPU inference via llama.cpp. Includes a Synthe

14
/ 100
Experimental
No License No Package No Dependents
Maintenance 13 / 25
Adoption 0 / 25
Maturity 1 / 25
Community 0 / 25

How are scores calculated?

Stars

—

Forks

—

Language

Python

License

—

Category

llm-finetuning-frameworks

Last pushed

Mar 28, 2026

Commits (30d)

0

GitHub
LLM Finetuning Frameworks · 85 frameworks

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/dakshjain-1616/gemma-3-12b-medical-sft"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Higher-rated alternatives

limix-ldm-ai/LimiX

LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence...

54

XXO47OXX/layer-scan

Automated LLM layer duplication config scanner — find the optimal (i,j) for any model + task

53

tatsu-lab/stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

48

google-research/plur

PLUR (Programming-Language Understanding and Repair) is a collection of source code datasets...

44

thuml/LogME

Code release for "LogME: Practical Assessment of Pre-trained Models for Transfer Learning" (ICML...

39

Explore ML Frameworks

All categories Trending ML Framework directory Insights