README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - text-generation
  - gguf
  - gemma
  - summarization
base_model: google/gemma-3-270m-it
model_type: gemma

catnip-summarizer

Fine-tuned Gemma-3-270M for task summarization and branch naming. It's meant to be used summarize user requests to coding agents. For example:

ollama run --verbose hf.co/vanpelt/catnip-summarizer "Help me make the vibes good"
Make Good Vibes
feat/make-good-vibes

The summary and git branch name can be used by tools like Catnip to keep multiple coding agent sessions organized.

Model Details

• Base Model: google/gemma-3-270m-it
• Format: GGUF
• Quantization: Q4_K_M
• Use Case: Generating concise task titles and git branch names

Training

• Training Run: https://wandb.ai/vanpelt/summarizer/runs/jh27ahps
• Repo: https://github.com/vanpelt/summarizer

Usage

Web Demo

You can try the model in your browser!

With Ollama

ollama run hf.co/vanpelt/catnip-summarizer "Help me make the vibes good"

With llama.cpp

# Download the GGUF file
huggingface-cli download vanpelt/catnip-summarizer gemma3-270m-summarizer-Q4_K_M.gguf

# Run with llama.cpp
./main -m gemma3-270m-summarizer-Q4_K_M.gguf -p 'Your prompt here'

Files

• tokenizer.json (31.8 MB)
• tokenizer_config.json (1.1 MB)
• added_tokens.json (0.0 MB)
• chat_template.jinja (0.0 MB)
• Modelfile (0.0 MB)
• template (0.0 MB)
• system (0.0 MB)
• gemma3-270m-summarizer-Q4_K_M.gguf (241.4 MB)
• special_tokens_map.json (0.0 MB)
• config.json (0.0 MB)
• params (0.0 MB)
• tokenizer.model (4.5 MB)