A minor PR for updating Colab notebook for re-ranker, updating main README etc.

README.md

@@ -133,10 +133,9 @@ For more information, see:
 | Section | Description |
 |-|-|
 | 📒 [Documentation](https://primeqa.github.io/primeqa) | Full API documentation and tutorials |
+| 📓 [Tutorials: Jupyter Notebooks](https://github.com/primeqa/primeqa/blob/main/docs/tutorials/index.md) | Notebooks to get started on QA tasks with PrimeQA |
 | 🏁 [Quick tour: Entry Points for PrimeQA](https://github.com/primeqa/primeqa/tree/main/primeqa) | Different entry points for PrimeQA: Information Retrieval, Reading Comprehension, TableQA and Question Generation |
-| 📓 [Tutorials: Jupyter Notebooks](https://github.com/primeqa/primeqa/tree/main/notebooks) | Notebooks to get started on QA tasks |
-| 📓 [GPT-3/ChatGPT Reader Notebooks](https://github.com/primeqa/primeqa/tree/main/notebooks/mrc/LLM_reader_predict_mode.ipynb) | Notebooks to get started with the GPT-3/ChatGPT reader components|
-| 💻 [Examples: Applying PrimeQA on various QA tasks](https://github.com/primeqa/primeqa/tree/main/examples) | Example scripts for fine-tuning PrimeQA models on a range of QA tasks |
+| 💻 [Extensions: Applying PrimeQA on various QA tasks](https://github.com/primeqa/primeqa/tree/main/extensions/README.md) | Example scripts for fine-tuning PrimeQA models on a range of QA tasks and replicate academic papers |
 | 🤗 [Model sharing and uploading](https://huggingface.co/docs/transformers/model_sharing) | Upload and share your fine-tuned models with the community |
 | ✅ [Pull Request](https://primeqa.github.io/primeqa/pull_request_template.html) | PrimeQA Pull Request |
 | 📄 [Generate Documentation](https://primeqa.github.io/primeqa/README.html) | How Documentation works |        

docs/tutorials/index.md

@@ -16,4 +16,3 @@ No worries we got you covered. These tutorials will get you acquainted with the
 | Generative QA: Retrieve and Generate (RAG) with Neural retrievers and readers from either HuggingFace or OpenAI models | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1cJ3BzLIdgKbayQFZB4QWTRIF0B92CHYa)  | [02_Retrieve_and_Generate_Answers_to_Questions_with_RAG.ipynb](02_Retrieve_and_Generate_Answers_to_Questions_with_RAG.ipynb)
 | Bring your own search and re-rank with PrimeQA embeddings | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1zPypFF88PNEyFmi-CtQnVHYhZOMdzQVt)  | [03_ReRank_search_results.ipynb](03_ReRank_search_results.ipynb)
 | Build QA models by fine-tuning LLMs with QLORA algorithm | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1qkVvYJOUonE5eLQQozqTkZtHlCqfY6Un)  | [04_Finetune_LLM_for_QA_with_QLORA.ipynb](04_Finetune_LLM_for_QA_with_QLORA.ipynb)
-

extensions/README.md

@@ -0,0 +1,5 @@
+# PrimeQA Extensions
+
+Under extensions, we have all the scripts necessary to perform experiments to train (fine-tune) and validate the models from academic benchmarks / papers. The general recommendation is to "use" PrimeQA components and not re-write tools that we already have under the main [PrimeQA entry-points](https://github.com/primeqa/primeqa/tree/main/primeqa/components) e.g. Reader components, Retriever components, Generator components.
+
+Take a look at the individual directories that contains the code for the algorithms that use various PrimeQA components for doing experiments.