Update README.md

README.md

@@ -17,6 +17,11 @@ Women's health is a critical and often underserved topic, with limited accessibl
 
 ```python
 
+from unsloth import FastLanguageModel
+import torch
+from transformers import TextStreamer, AutoTokenizer
+
+
 max_seq_length = 2048
 dtype = None
 load_in_4bit = False
@@ -64,12 +69,12 @@ if not use_streamer:
 
 ## Dataset
 
-The dataset was prepared through a comprehensive process to ensure quality and relevance. Health-related websites were scraped, open-source e-books and PDFs focusing on women's health were collected, and an instruction dataset was created from these sources. To generate high-quality questions, we utilized the gemini-flash model, ensuring the dataset’s alignment with the domain.
+The dataset was prepared through a comprehensive process based on our synthetic dataset generation method. Health-related websites were scraped, open-source e-books and PDFs focusing on women's health were collected, and an instruction dataset was created from these sources. To generate high-quality questions, we utilized a technique that involves role-playing  between two LLMs and contextually-augmented by RAG.
 The dataset will be made publicly available through its dedicated repository [altaidevorg/women-health-mini](https://huggingface.co/datasets/altaidevorg/women-health-mini). Additionally, the code used for dataset generation will be released in the future to promote transparency and enable reproducibility.
 
 ## Evaluation Notes
 
-During testing, we observed that the LoRA checkpoint performed better in evaluations compared to the version where the LoRA checkpoint was merged with the base model. Interestingly, the standalone LoRA checkpoint consistently delivered superior results, though we currently lack a concrete explanation for this phenomenon.
+During testing, we observed that the LoRA checkpoint performed better in evaluations compared to the version where the LoRA checkpoint was [merged with the base model](https://huggingface.co/altaidevorg/gemma-women-health-merged). Interestingly, the standalone LoRA checkpoint consistently delivered superior results, though we currently lack a concrete explanation for this phenomenon.
 We are actively investigating the underlying cause, with our best hypothesis being that the merging process may introduce some form of precision loss. Further research is underway to validate this theory and optimize the performance.
 
 ### Disclaimer