Downloads · 30 days
47
15% of all-time downloads
AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF
Qwen2.5-0.5B-Instruct-summarization-GGUF is a machine learning model from AbdelilahYounsi. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Fine-tuned Qwen2.5-0.5B-Instruct for news article summarization. Trained on CNN DailyMail dataset and converted to GGUF format for efficient inference.
Downloads · 30 days
47
15% of all-time downloads
All-time downloads
307
Public
Repo size
994 MB
Likes
0
Public
Click a slice to open those files.
.gguf994 MB · 100%
From the Hugging Face model README
Fine-tuned Qwen2.5-0.5B-Instruct for news article summarization. Trained on CNN DailyMail dataset and converted to GGUF format for efficient inference.
| Metric | Base | Fine-tuned | Δ |
|---|---|---|---|
| ROUGE-1 | 0.239 | 0.268 | +11% |
| ROUGE-2 | 0.070 | 0.082 | +16% |
| ROUGE-L | 0.171 | 0.198 | +16% |
| ROUGE-Lsum | 0.196 | 0.251 | +28% |
llama.cpp:
./llama-cli -hf AbdelilahYounsi/Qwen2.5-0.5B-Instruct-summarization-GGUF --jinja
Ollama:
ollama create qwen-summarizer -f Modelfile
ollama run qwen-summarizer
Prompt format:
Summarize the following text:
[Your article text here]
Apache 2.0