Cleaned up README

README.md

@@ -13,26 +13,38 @@ model_type: gemma
 
 # catnip-summarizer
 
-Fine-tuned Gemma-3-270M for task summarization and branch naming
+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:
+
+```shell
+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](https://github.com/wandb/catnip) to keep multiple coding agent sessions organized.
 
 ## Model Details
 
 - **Base Model**: google/gemma-3-270m-it
-- **Format**: GGUF (quantized for efficient inference)
+- **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](https://wandb.ai/vanpelt/summarizer/runs/jh27ahps)
+- **Repo**: [https://github.com/vanpelt/summarizer](https://github.com/vanpelt/summarizer)
 
 ## Usage
 
+### Web Demo
+
+You can [try the model](https://vanpelt.github.io/summarizer/) in your browser!
+
 ### With Ollama
 
 ```bash
-ollama pull hf.co/vanpelt/catnip-summarizer
-ollama run hf.co/vanpelt/catnip-summarizer
+ollama run hf.co/vanpelt/catnip-summarizer "Help me make the vibes good"
 ```
 
 ### With llama.cpp
@@ -54,7 +66,6 @@ huggingface-cli download vanpelt/catnip-summarizer gemma3-270m-summarizer-Q4_K_M
 - `Modelfile` (0.0 MB)
 - `template` (0.0 MB)
 - `system` (0.0 MB)
-- `model.safetensors` (511.4 MB)
 - `gemma3-270m-summarizer-Q4_K_M.gguf` (241.4 MB)
 - `special_tokens_map.json` (0.0 MB)
 - `config.json` (0.0 MB)