link in read me

README.md

@@ -10,8 +10,11 @@ pinned: false
 license: mit
 ---
 
+
 ## Overview 
 
+[Link to Application](https://huggingface.co/spaces/ebbalg/Iris)
+
 This project demonstrates the fine tuning of a LLaMA 3.2 3B model using the QLoRA strategy. In this method, the model's original weights are frozen and small "adapters" matrices are trained. This type of fine tuning drastrically reduces the number of parameters to train, which is significant when starting with LLMs with billions of parameters. QLoRA is an extension of this, where weights are quantized in a compress format, speeding up the entire process.
 
 In this Lab, the LLaMA 3.2 3B model is fine tuned using the FineTome-100k dataset, which is a dataset containing instructions (or questions) and answers. The fine tuned model is serviced in a Gradio app like a chatbot. The chatbot was repurposed to be an AI teacher assistant, helping students answer questions or explain concepts about machine learning. 
@@ -44,6 +47,6 @@ The drop in accuracy is expected for the ARC dataset: fine-tuning encourages the
 
 ## Improvements
 
-1. The chatbot keeps little context of previous conversations. We could save each prompt and output (conversation) and feed it again to the LLM so that it has more context of previous responses. This could be done dynamically so it keeps a certain length of conversation.
+1. The chatbot keeps little context of previous conversations and we do not inject back the output from previous answers because the inference was too slow. This is fitting for a question-answer interaction with the LLM, since context from previous answers is not as important. We could build a smart way of detection if the user is asking a follow up question, and only in those cases add the previous answer as context to the prompt sent to the LLM. This can be done dynamically to toggle on and off the context addition and make the experience better for the user.
 
 2. The quiz is generated by an LLM that is far from being 100% accurate in reasoning and answering questions. For this to be of more value we should give feedback to the LLM when the answer it selects as correct is in fact false (or other answers are correct). We tried looking for an ML-themed dataset for further fine tuning the LLM but couldn't find any. But this would greatly improve the quality of the generated quizes.