llama2

This repository contains a web application designed to execute relatively compact, locally-operated Large Language Models (LLMs).

Modular Rust transformer/LLM library using Candle

LangChain, Llama2-Chat, and zero- and few-shot prompting are used to generate synthetic datasets for IR and RAG system evaluation

Instruction/chat prompts creation library for text generation LLMs. It supports local and Hugging Face models.

CSVs of the Huggingface and LMArena LLM leaderboards, along with the code to generate them in Python and R.

The AI Radiologist You Can Chat With

An open source framework for Retrieval-Augmented System (RAG) uses semantic search helps to retrieve the expected results and generate human readable conversational response with the help of LLM (Large Language Model).

LLMs based multi-model framework for building AI apps.

This notebook contains the code script I used to fine tune a Llama-2 LLM to create a python codeium generator using a custom build dataset

Open Translator: Speech To Speech and Speech to text Translator with voice cloning and other cool features

Perform RAG (Retrieval-Augmented Generation) from your PDFs using this Colab notebook! Powered by Llama 2

Our Process for Llama2 Finetuning

This repo contains almost everything about Generative Ai

This is AlpaGasus2-QLoRA based on LLaMA2 with AlpaGasus mechanism using QLoRA!

A LLaMA2-7b chatbot with memory running on CPU, and optimized using smooth quantization, 4-bit quantization or Intel® Extension For PyTorch with bfloat16.

We introduce a large semi-automatically generated dataset of ~400,000 descriptive sentences about commonsense knowledge that can be true or false in which negation is present in about 2/3 of the corpus in different forms that we use to evaluate LLMs

An implementation of LazyLLM token pruning for LLaMa 2 model family.

LLM, Fine Tuning, Llama 2, Gemma, Mixtral, vLLM, LangChain, RAG, ChromaDB, FAISS

Build LLM-enabled FastAPI applications without build configuration.

⚡ LLaMA-2 model experiment