ChTauchmann

llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

FlagEmbedding

Retrieval and Retrieval-augmented LLMs

Verba

Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

mergekit

Tools for merging pretrained large language models.

LongLoRA

Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)

Medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

langserve

LangServe 🦜️🏓

self-rag

This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

RAG-Survey

pyserini

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

long_llama

LongLLaMA is a large language model capable of handling long contexts. It is based on OpenLLaMA and fine-tuned with the Focused Transformer (FoT) method.

llama-lab

LLMTest_NeedleInAHaystack

Doing simple retrieval from LLM models at various context lengths to measure accuracy

Awesome-LLM-Reasoning

Reasoning in Large Language Models: Papers and Resources, including Chain-of-Thought, Instruction-Tuning and Multimodality.

TransformerLens

A library for mechanistic interpretability of GPT-style language models

gritlm

Generative Representational Instruction Tuning

Causality4NLP_Papers

A reading list for papers on causality for natural language processing (NLP)

tevatron

Tevatron - A flexible toolkit for neural retrieval research and development.

landmark-attention

Landmark Attention: Random-Access Infinite Context Length for Transformers

task_vectors

Editing Models with Task Arithmetic

distilling-step-by-step

dpr-scale

Scalable training for dense retrieval models.

soft-moe-pytorch

Implementation of Soft MoE, proposed by Brain's Vision team, in Pytorch

ACL2023-Retrieval-LM.github.io

https://acl2023-retrieval-lm.github.io/

OpenMatch

An Open-Source Package for Information Retrieval

DallEval

DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models (ICCV 2023)

RAG-query-rewriting

fneval

Functional Benchmarks and the Reasoning Gap

icl_task_vectors

belief-localization

This repository includes code for the paper "Does Localization Inform Editing? Surprising Differences in Where Knowledge Is Stored vs. Can Be Injected in Language Models."