---
license: mit
tags:
  - gpt2
  - ubuntu
  - linux
  - support
  - gguf
  - ollama
language:
  - en
---

# Ubuntu Support LLM

A small GPT2-based model (51M params) fine-tuned on Ubuntu Q&A dialogue.
Refuses all non-Ubuntu questions.

## Model Details
- Architecture: GPT2 (512 embd, 8 layers, 8 heads)
- Training data: sedthh/ubuntu_dialogue_qa (~12k records)
- Epochs: 5 | Loss: 2.076
- Quantization: Q4_K_M (40 MB)

## Run with Ollama
```bash
ollama create ubuntu-support -f Modelfile
ollama run ubuntu-support
```