llm.create_chat_completion(
messages = "No input example has been defined for this model task."
)GeoThreat Gemma 3 4B
Fine-tuned GeoThreat Gemma 3 4B for threat intelligence summarisation.
Training Details
- Base model: google/gemma-3-4b-it
- Method: LoRA SFT + DPO
- Quantisation: GGUF Q6_K
- Training date: 2026-06-08
- Dataset size: 157735 examples
Training Metrics
SFT
| Metric | Value |
|---|
DPO
| Metric | Value |
|---|
Usage
ollama create geothreat-gemma3 -f Modelfile
ollama run geothreat-gemma3
- Downloads last month
- -
Hardware compatibility
Log In to add your hardware
6-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="joeh-ops/geothreat-gemma3-4b", filename="", )