Update README.md

README.md

@@ -9,28 +9,69 @@ tags:
 licence: license
 ---
 
-# Model Card for distilgpt2-dpo-checkpoint
+# Preference-Tuned Summarizer using Direct Preference Optimization (DPO)
 
-This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2).
-It has been trained using [TRL](https://github.com/huggingface/trl).
+This repository hosts a lightweight text summarization model fine-tuned from DistilGPT2 using Direct Preference Optimization (DPO). The model was trained on preference-labeled data to generate summaries that align better with human preferences compared to traditional supervised fine-tuning.
 
-## Quick start
+---
+
+## Model Details
+
+- **Base model:** DistilGPT2
+- **Fine-tuning method:** Direct Preference Optimization (DPO)
+- **Dataset:** Preference pairs with `prompt`, `chosen`, and `rejected` summaries
+- **Evaluation metrics:** ROUGE-1 (0.2841), ROUGE-L (0.2247), BLEU (0.0286)
+- **Use case:** Generating high-quality, human-aligned text summaries
+
+---
+
+## How to Use
+
+You can load and use the model easily with the Hugging Face Transformers library:
 
 ```python
 from transformers import pipeline
 
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="None", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
+summarizer = pipeline("text-generation", model="justthzz/preference-tuned-summarizer")
+text = "Summarize: Your input text here."
+
+summary = summarizer(text, max_length=150, do_sample=False)
+print(summary[0]['generated_text'])
 ```
 
-## Training procedure
+---
+
+## Files Included
+
+- `pytorch_model.bin` - Model weights
+- `config.json` - Model configuration
+- Tokenizer files (`tokenizer.json`, `vocab.txt`, etc.)
+- Model card and this README
 
- 
+---
+
+## About DPO
+
+Direct Preference Optimization is a fine-tuning technique that leverages preference-labeled datasets to directly optimize a model’s output preferences. This method improves alignment with human judgments beyond typical supervised fine-tuning.
+
+---
+
+## Evaluation Results
 
+| Metric   | Base Summary (avg) | DPO Summary (avg) |
+|----------|--------------------|-------------------|
+| ROUGE-1  | 0.0442             | **0.2841**        |
+| ROUGE-L  | 0.0366             | **0.2247**        |
+| BLEU     | 0.0000             | **0.0286**        |
 
-This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
+---
+
+## Links
+
+- [GitHub Repository](https://github.com/justthzz/preference-tuned-summarizer)  
+- [Model on Hugging Face](https://huggingface.co/justthzz/preference-tuned-summarizer)
+
+---
 
 ### Framework versions