Update README.md

README.md

@@ -1,6 +1,121 @@
 ---
+language:
+- en
+tags:
+- qwen2
+- text-generation
+- summarization
+- key-points
+- blog-summarization
 datasets:
 - ncls-p/blog-key-points
-base_model:
-- unsloth/Qwen2.5-7B-Instruct
----
+license: cc-by-4.0
+base_model: Qwen/Qwen2.5-7B-Instruct
+---
+
+# Qwen2.5-7B-blog-key-points
+
+This model is fine-tuned from [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the [blog-key-points dataset](https://huggingface.co/datasets/ncls-p/blog-key-points). It specializes in extracting key points from blog articles and web content, providing concise bullet-point summaries that capture the essential information.
+
+## Model Description
+
+**Qwen2.5-7B-blog-key-points** is a 7B parameter model fine-tuned specifically for the task of extracting key points from articles. It can process a full article and generate a concise, bullet-point summary highlighting the most important information. Compared to the 3B version, this model offers enhanced capabilities for understanding complex articles and generating more nuanced summaries.
+
+### Model Details
+
+- **Model Type:** Qwen2.5 (7B parameters)
+- **Base Model:** [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct)
+- **Training Dataset:** [ncls-p/blog-key-points](https://huggingface.co/datasets/ncls-p/blog-key-points)
+- **Language:** English
+- **License:** [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/)
+- **Finetuning Approach:** Instruction fine-tuning on article-summary pairs
+
+## Uses
+
+### Direct Use
+
+This model is designed for extracting key points from articles. You can use it directly for:
+
+- Summarizing blog posts
+- Extracting important information from news articles
+- Creating bullet-point summaries of long-form content
+- Generating concise overviews of research papers
+- Distilling complex information into digestible points
+
+### Example Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "ncls-p/Qwen2.5-7B-blog-key-points"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+article = """
+[Your article text here]
+"""
+
+prompt = f"""
+Extract the key points from the following article:
+
+{article}
+"""
+
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_length=1024)
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+print(response)
+```
+
+## Training
+
+The model was fine-tuned on the [blog-key-points dataset](https://huggingface.co/datasets/ncls-p/blog-key-points), which contains 200 article-summary pairs. Each pair consists of a full article and a bullet-point summary of key points extracted using Perplexity AI.
+
+### Training Procedure
+
+- **Fine-tuning Framework:** [Unsloth](https://github.com/unslothai/unsloth)
+- **Training Data Format:**
+  ```json
+  {
+    "instruction": "",
+    "input": "Full article content",
+    "output": "Here are the key points of the article:\n* Key point 1\n* Key point 2\n* Key point 3\n..."
+  }
+  ```
+
+## Evaluation
+
+The model was evaluated on its ability to extract relevant key points from articles not seen during training. Evaluation metrics focused on:
+
+1. **Relevance:** How well the extracted points capture the main ideas of the article
+2. **Conciseness:** The ability to summarize information in a clear, bullet-point format
+3. **Completeness:** Whether all important information is captured in the summary
+4. **Coherence:** The logical flow and organization of the extracted points
+
+## Limitations and Biases
+
+- The model may inherit biases present in the training data, including potential biases in the source articles or in the key point extraction process.
+- Performance may vary depending on the length, complexity, and domain of the input article.
+- The model is primarily trained on English-language content and may not perform well on content in other languages.
+- As with any summarization model, there is a risk of omitting important information or misrepresenting the original content.
+- While the 7B parameter size offers improved capabilities over the 3B version, it also requires more computational resources to run.
+
+## How to Cite
+
+If you use this model in your research, please cite:
+
+```bibtex
+@misc{qwen25-7b-blog-key-points,
+  author = {ncls-p},
+  title = {Qwen2.5-7B-blog-key-points},
+  year = {2024},
+  publisher = {Hugging Face},
+  journal = {Hugging Face model repository},
+  howpublished = {\url{https://huggingface.co/ncls-p/Qwen2.5-7B-blog-key-points}},
+}
+```
+
+## Dataset Creation
+
+The dataset used to train this model was created using the [Dataset Enhancer with Perplexity AI](https://github.com/ncls-p/pplx-to-dataset), a CLI tool that extracts key points from web articles using Perplexity AI's API and adds them to a dataset in a structured format.