Update README.md

README.md

@@ -1,3 +1,28 @@
 ---
 license: apache-2.0
 ---
+
+# MiniSymposium Demo Release
+MiniSymposium is an experimental QLora model that I created based on Mistral 7b. I created it attempting to achieve these goals:
+
+1. Demonstrate the untapped potential of using a small, focused dataset of handwritten examples instead of training on a large amount of synthetic GPT outputs
+2. Create a dataset that allows the model to explore different possible answers from multiple perspectives before reaching a conclusion.
+3. Develop a model that performs well across various prompt formats, rather than overfitting to a specific kind of format
+
+The current trend in QLora/Lora-based finetuning (and finetuning in general for local LLMs) is to use large synthetic datasets. These are usually GPT datasets that are trained with higher learning rates.
+
+However, I believe there is a lot of potential in using small, hand-written datasets with low learning rates, even if it's for general-purpose instruction following, as long as you train it for many epochs on a learning rate low enough to avoid overfitting.
+
+This approach, I hypothesize, helps the model to leam the deeper pattem of instruction following instead of fitting toward shallow data biases (like "As an AI made by OpenAI" and other GPT-isms) that ignore deeper instruction following patterns.
+
+My initial configuration for this QLora model used a constant learning rate of 1e-6 (0.000001), which resulted in overfitting after approximately 100 epochs. The model started reproducing the original dataset amost verbatim and exhibited poor generalization across different prompt formats, including obvious hallucinations & also Chinese language outputs for some reason.
+
+However, turning down the learning rate to 1/10th of (1e-7, which is 0.0000001) significantly improved the model. I trained for about ~10 hours on my RTX 3060 to 600 epochs; I think it's still a little undertrained, but I encourage people to try the demo model out.
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6491e00e057b0928b3e07b75/WOebITt3TuTUPZSdi4VDV.png)
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6491e00e057b0928b3e07b75/vyWIl_NBf6COtFoW29w7I.png)
+
+The dataset is about 200 lines worth of data in the special format that has multiple 'perspectives' to the same answer.
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6491e00e057b0928b3e07b75/hZ4cmmSTUk1R6WCS54Ees.png)