llama2

The tutorials include related topics langchain, llama 2, petals, and pinecone

Llama2 finetuning framework of Q&A from transcription of YouTube videos

Imagine an application that autonomously take down notes for you during meetings, lectures, and conversations. Check this out...

Fine tune Large Language Model on Mathematic dataset

Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B fine-tuned model, optimized for dialogue use cases and converted for the Hugging Face Transformers format. Links to other models can be found in the index at the bottom.

Financial Bot with Llama 2(quantized model) It quickly answers financial queries using the llama-2-7b-chat.ggmlv3.q4_0.bin model

FineTuning LLMs and MLs models

A comprehensive guide and codebase for fine-tuning Large Language Models (LLMs). This repository provides step-by-step tutorials, example scripts, and best practices for fine-tuning LLMs using popular frameworks like PyTorch and Hugging Face Transformers.

Secure Your Contract: Towards Efficient and Reliable AI-Assisted Contract Drafting

MediChat: An AI-powered medical chatbot using the Llama-2-7B-Chat model for precise clinical responses. Integrates Chroma DB and all-MiniLM-L6-v2 embeddings trained on medical literature, including texts like Clinical Emergency Medicine and Gale Encyclopedia. Accurate, fast, and reliable for healthcare queries.

An End to End Medical Chatbot Project Using Llama2, LangChain, Flask, Pinecone

An ai powered resume feedback site

Small document chatbot using LlamaIndex and Llama-2

Llama-2-7B fine-tuned with QLoRA for personalized financial literacy Q&A — Flask web interface included.

Unveil Customer Insights: Sentiment Analysis Reimagined

Welcome to TurboInference, a high-performance inference toolkit written in C++ for rapid and efficient deployment of LLM models. This GitHub repository provides a comprehensive set of tools and utilities designed to make inference tasks swift and resource-efficient.

Litigate leverages state-of-the-art large language models such as GPT-3.5, GPT-3.5 Turbo, GPT-4.0, and LLaMA 2 to provide expert legal advice on household and tenant law.

Building llama 2 from scratch.

A chatbot that introduce myself and answer questions related to my experience of software development.

This project uses the LLAMA 2 model to generate blog content. The application provides an interface to input prompts and receive generated text based on those prompts.