## UA DSI LLM Chatbots: *Chatur project*

Space for project development

:bookmark_tabs: :point_right: **Mithun's [Google Doc "Chatur" project description](https://docs.google.com/document/d/1nMcs8rgbAQn2xLBJsfFDEFkhEZkG7K5WIhh0INxdY4I/edit#heading=h.i8is4e2gnlxl)**

## Goals

| Products | Description |
| :-- | :-- |
| Tutor - Bots | Lectures, Readings, HTML, .pptx, PDFs, .docx, .md, .csv, .txt |
| Assistants | Course-work |
| | Tutors |
| | Knowledge-based |
| Research - Q&A documents | PDFs, text |
| Industry partners to UA | Knowledge-based |

***

**Collection of readings posted in our Slack:**

* [HuggingFace Chatbot Arena Leaderboard](https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard)
* [Intel extension for transformers](https://github.com/intel/intel-extension-for-transformers)
* [Langchain](https://blog.langchain.dev/langchain-chat/)
* [LLM360: Fully Transparent Open-Source LLMs](https://www.llm360.ai/blog/introducing-llm360-fully-transparent-open-source-llms.html)
* [Practical Tips for Finetuning LLMs Using LoRA (Low-Rank Adaptation)](https://magazine.sebastianraschka.com/p/practical-tips-for-finetuning-llms#:~:text=Low%2Drank%20adaptation%20(LoRA),technique%20worth%20familiarizing%20oneself%20with.)
* [Microsoft promptbase](https://github.com/microsoft/promptbase)
* [NVIDIA NeMo Framework](https://www.nvidia.com/en-us/ai-data-science/generative-ai/nemo-framework/)
* [NVIDIA NeMo Guardrails](https://github.com/NVIDIA/NeMo-Guardrails)
* [oobabooga](https://github.com/oobabooga)
* [oobabooga/text-generation-webui](https://github.com/oobabooga/text-generation-webui/wiki)
* [Panel chat examples](https://holoviz-topics.github.io/panel-chat-examples/)
* [MLflow LLM Evaluate](https://mlflow.org/docs/latest/llms/llm-evaluate/index.html)
* [PromtEngineering/localGPT](https://github.com/PromtEngineer/localGPT)
* [Retrieval-Augmented Generation (RAG) demo](https://github.com/outerbounds/rag-demo)
* [Retrieval-Augmented Generation: How to Use Your Data to Guide LLMs](https://outerbounds.com/blog/retrieval-augmented-generation/)
* [Retrieval-Augmented Generation Chatbot, How to build a...](https://www.anaconda.com/blog/how-to-build-a-retrieval-augmented-generation-chatbot)

***

### Other references...

* [Big Bench. Beyond the Imitation Game collaborative benchmark](https://github.com/google/BIG-bench)
* [LoRA (Low-Rank Adaptation of Large Language Models)](https://huggingface.co/docs/diffusers/main/en/training/lora)
* [RAG (Retrieval-Augmented Generation)](https://blogs.nvidia.com/blog/what-is-retrieval-augmented-generation/), [[opt 2]](https://www.oracle.com/artificial-intelligence/generative-ai/retrieval-augmented-generation-rag/)
* [Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents](https://github.com/Zoeyyao27/CoT-Igniting-Agent?tab=readme-ov-file#igniting-language-intelligence-the-hitchhikers-guide-from-chain-of-thought-reasoning-to-language-agents)
* [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness)
***

***

Created: 12-13-2023

Updated: 12-13-2023