Update README.md

README.md

@@ -4,15 +4,25 @@ license: apache-2.0
 base_model: Falconsai/text_summarization
 tags:
 - generated_from_trainer
+- summarization
+- compression
+- prompt-summarization
+- prompt-compression
+- text_summarization
+- text_compression
 metrics:
 - rouge
 model-index:
 - name: very-small-prompt-compression
   results: []
+datasets:
+- gravitee-io/dolly-15k-prompt-compression
 ---
 
 # very-small-prompt-compression
 
+Interactive demo: [Very Small Prompt Compression (Space)](https://huggingface.co/spaces/gravitee-io/very-small-prompt-compression-demo)
+
 This model is a fine-tuned version of [Falconsai/text_summarization](https://huggingface.co/Falconsai/text_summarization) on the [gravitee-io/dolly-15k-prompt-compression](https://huggingface.co/datasets/gravitee-io/dolly-15k-prompt-compression) dataset.  
 It achieves the following results on the evaluation set:
 - Loss: 2.1583
@@ -109,3 +119,29 @@ The following hyperparameters were used during training:
 - **Held-out compression:** On the ≤64 token evaluation split the model reaches a mean compression ratio of 0.7395 (≈26 % token reduction) with only 0.04 % of generations exceeding the original length.
 - **Semantic fidelity:** Cosine similarity between original and compressed embeddings (`text-embedding-3-small`) averages above 0.90, indicating that key semantics are preserved.
 - **Instruction alignment:** ROUGE-L of 0.7792 against synthetic targets shows the model closely matches the policy-compliant outputs produced during data generation.
+
+## License
+This model is released under the Apache 2.0 License.
+
+## Acknowledgments
+- Training data sourced from [databricks/databricks-dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k) and the compressed derivative [gravitee-io/dolly-15k-prompt-compression](https://huggingface.co/datasets/gravitee-io/dolly-15k-prompt-compression)
+- Base model: [Falconsai/text_summarization](https://huggingface.co/Falconsai/text_summarization)
+
+## Citation
+If you use this model in your research, please cite:
+
+```
+@misc{very_small_prompt_compression_2025,
+  title={Very Small Prompt Compression Model},
+  author={Derek Thompson - Gravitee.io},
+  year={2025},
+  publisher={Hugging Face},
+  howpublished={\url{https://huggingface.co/gravitee-io/very-small-prompt-compression}}
+}
+```
+
+## Contact
+For questions, issues, or contributions, please open an issue on the model repository.
+
+---
+Generated by [dotslashderek](https://huggingface.co/dotslashderek) on 2025-10-31