dawidm

ChatGPT

🔮 ChatGPT Desktop Application (Mac, Windows and Linux)

ChatGLM-6B

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

vllm

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

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

dalai

The simplest way to run LLaMA on your local machine

trl

Train transformer language models with reinforcement learning.

fuzzywuzzy

Fuzzy String Matching in Python

txtai

💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows

CogVideo

Text-to-video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

exllama

A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.

mamba-minimal

Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

sparseml

Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models

CodeGPT

JetBrains extension providing access to state-of-the-art LLMs, such as GPT-4, Claude 3, Code Llama, and others, all for free

splade

SPLADE: sparse neural search (SIGIR21, SIGIR22)

tensor_parallel

Automatically split your PyTorch models on multiple GPUs for training & inference

torchkge

TorchKGE: Knowledge Graph embedding in Python and PyTorch.

Sophia

Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.

diffq

DiffQ performs differentiable quantization using pseudo quantization noise. It can automatically tune the number of bits used per weight or group of weights, in order to achieve a given trade-off between model size and accuracy.

DAGNN

A graph neural network tailored to directed acyclic graphs that outperforms conventional GNNs by leveraging the partial order as strong inductive bias besides other suitable architectural features.

timelms

TimeLMs: Diachronic Language Models from Twitter

phi2-finetune

multi-imbalance

Python package for tackling multi-class imbalance problems. http://www.cs.put.poznan.pl/mlango/publications/multiimbalance/

BAN-PL

Polish Dataset of Banned Harmful and Offensive Content from Wykop.pl web service

abstention

Algorithms for abstention, calibration and domain adaptation to label shift.

POLITICS

Code, data, and models for "POLITICS: Pretraining with Same-story Article Comparison for Ideology Prediction and Stance Detection"

LED

Source code of paper 'LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrieval' (WWW 2023)

PT-HCL

[WWW 2022] Zero-Shot Stance Detection via Contrastive Learning

Anima

Moved to here: https://github.com/lyogavin/airllm