4th Place Solution for the Kaggle Competition: LMSYS - Chatbot Arena Human Preference Predictions
-
Updated
Oct 24, 2024 - Jupyter Notebook
4th Place Solution for the Kaggle Competition: LMSYS - Chatbot Arena Human Preference Predictions
Gemma2(9B), Llama3-8B-Finetune-and-RAG, code base for sample, implemented in Kaggle platform
Effortless Data Extraction, Powered by : Generative AI
📝 Blog Writer Crew AI Agents - Streamlit App 🖋️
📝 Streamlit App : Weekly News Letter Crew AI Agents 🖋️
An Intelligent Health LLM System for Personalized Medication Guidance and Support.
Analyze a dataset of conversations from the Chatbot Arena, where various LLMs provide responses to user prompts. The goal is to develop a model that enhances chatbot interactions, ensuring they align more closely with human preferences.
This competition challenges you to predict which responses users will prefer in a head-to-head battle between chatbots powered by large language models (LLMs).
GroqWarp is a Streamlit app that compares the performance of RAG using Groq and Ollama models, visualizing response times and accuracy. It leverages FAISS for document retrieval and displays a side-by-side performance chart.
Tools and method for fine-tuning the Gemma 2 model on custom datasets
Streamlit based RAG for interactive Q&A using Groq AI and various open-source LLM models. Upload PDFs, create vector embeddings, and query documents for context-based answers.
A next-generation creative writing large language model for writing entire book chapters at once.
Add a description, image, and links to the gemma2-9b topic page so that developers can more easily learn about it.
To associate your repository with the gemma2-9b topic, visit your repo's landing page and select "manage topics."