Downloads · 30 days
0
gemma-facts-finetune
kayhani/gemma-facts-finetune
gemma-facts-finetune is a machine learning model from kayhani. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as gemma.
Access
Public
Updated Nov 23, 2025
Repo size
117 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors83.1 MB · 71%
At a glance
- License
- gemma
- Access
- Public
- Created
- Nov 23, 2025
- Updated
- Nov 23, 2025
- SHA
- c39a3de0
Model card
From the Hugging Face model README
🚧 Gemma 2 Facts (Work in Progress)
Status: Active Training.
Current State: Synthetic data generation pipeline is running.
Target: Fine-tuning Gemma 2 (9B/2B) for strict factual grounding using Direct Preference Optimization (DPO).
Project Goal
This model is being trained to solve the "hallucination" problem in RAG systems. It is aligned to refuse questions that cannot be answered strictly from the provided context document.
- Dataset: Custom synthetic expansion of the DeepMind FACTS Grounding benchmark.
- Method: DPO + QLoRA on consumer hardware (T4 GPU).
- License
- gemma
- Created
- Nov 23, 2025
- Updated
- Nov 23, 2025