HallerPatrick

text-generation-webui

A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.

vllm

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

pyo3

Rust bindings for the Python interpreter

broot

A new way to see and navigate directory trees : https://dystroy.org/broot

litellm

Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)

OpenLLM

Run any open-source LLMs, such as Llama 2, Mistral, as OpenAI compatible API endpoint in the cloud.

petals

🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading

cupy

NumPy & SciPy for GPU

photopea

Photopea is online image editor

nevergrad

A Python toolbox for performing gradient-free optimization

waveterm

An open-source, cross-platform terminal for seamless workflows

whisper-diarization

Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper

llama2.mojo

Inference Llama 2 in one file of pure 🔥

pezzo

🕹️ Open-source, developer-first LLMOps platform designed to streamline prompt design, version management, instant delivery, collaboration, troubleshooting, observability and more.

pdbpp

pdb++, a drop-in replacement for pdb (the Python debugger)

RetNet

An implementation of "Retentive Network: A Successor to Transformer for Large Language Models"

lm-format-enforcer

Enforce the output format (JSON Schema, Regex etc) of a language model

ToRA

ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].

dont-stop-pretraining

Code associated with the Don't Stop Pretraining ACL 2020 paper

langtest

Deliver safe & effective language models

RetNet

Huggingface compatible implementation of RetNet (Retentive Networks, https://arxiv.org/pdf/2307.08621.pdf) including parallel, recurrent, and chunkwise forward.

lsp-timeout.nvim

Start/stop LSP servers upon demand; keeps RAM usage low

nvim-test

A Neovim wrapper for running tests

xVal

Repository for code used in the xVal paper

EM_German

Repository for the EM German Model

fabricator

[EMNLP 2023 Demo] fabricator - annotating and generating datasets with large language models.

yet-another-retnet

A simple but robust PyTorch implementation of RetNet from "Retentive Network: A Successor to Transformer for Large Language Models" (https://arxiv.org/pdf/2307.08621.pdf)

Tnn

[ICLR 2023] Official implementation of Transnormer in our ICLR 2023 paper - Toeplitz Neural Network for Sequence Modeling

hgru-pytorch

Vocabulary-Transfer

Implementation of the paper "Fine-Tuning Transformers: Vocabulary Transfer" https://arxiv.org/pdf/2112.14569.pdf