ganler

tabby

Self-hosted AI coding assistant

text-generation-inference

Large Language Model Text Generation Inference

ragas

Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines

HyperDbg

State-of-the-art native debugging tool

weak-to-strong

magicoder

Magicoder: Source Code Is All You Need

OutlookGoogleCalendarSync

Sync your Outlook and Google calendars

gptq

Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

S-LoRA

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

AlpacaDataCleaned

Alpaca dataset from Stanford, cleaned and curated

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.

codealpaca

MergeLM

Codebase for Merging Language Models

flashinfer

FlashInfer: Kernel Library for LLM Serving

synthesizer

A multi-purpose LLM framework for RAG and data creation.

ml4se

A curated list of papers, theses, datasets, and tools related to the application of Machine Learning for Software Engineering

verus

Verified Rust for low-level systems code

llamafia.github

ezsh

quickly install zsh, oh-my-zsh with power-level-9k zsh-completions zsh-autosuggestions zsh-syntax-highlighting history-substring-search

llm_rules

RuLES: a benchmark for evaluating rule-following in language models

llm-decontaminator

Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"

FastEval

Fast & more realistic evaluation of chat language models. Includes leaderboard.

MultiPL-E

A multi-programming language benchmark for evaluating the performance of large language model of code.

TransformerPrograms

[NeurIPS 2023] Learning Transformer Programs

rocMLIR

py-tree-sitter-languages

Binary Python wheels for all tree sitter languages.

cceval

CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion (NeurIPS 2023)

PPOCoder

Code for the TMLR 2023 paper "PPOCoder: Execution-based Code Generation using Deep Reinforcement Learning"

vllm-rocm

vLLM: A high-throughput and memory-efficient inference and serving engine for LLMs