JoaoLages

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

Language:PythonMIT412400

PowerInfer

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

Language:C++MIT753900

ragas

Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines

Language:PythonApache-2.0548200

apted

Python APTED algorithm for the Tree Edit Distance

Language:PythonMIT8300

evalplus

Rigourous evaluation of LLM-synthesized code - NeurIPS 2023

Language:PythonApache-2.0101100

hallucination-leaderboard

Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents

Apache-2.0109100

alignment-handbook

Robust recipes to align language models with human and AI preferences

Language:PythonApache-2.0412500

promptflow

Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

Language:PythonMIT862600

Time-Series-Library

A Library for Advanced Deep Time Series Models.

Language:PythonMIT492800

ChatGPT-AutoExpert

🚀🧠💬 Supercharged Custom Instructions for ChatGPT (non-coding) and ChatGPT Advanced Data Analysis (coding).

Language:JavaScriptNOASSERTION652800

MemGPT

Create LLM agents with long-term memory and custom tools 📚🦙

Language:PythonApache-2.01063500

attention_sinks

Extend existing LLMs way beyond the original training length with constant memory usage, without retraining

Language:PythonApache-2.064500

CTGAN

Conditional GAN for generating synthetic tabular data.

Language:PythonNOASSERTION117500

SDV

Synthetic data generation for tabular data

Language:PythonNOASSERTION219500

datawig

Imputation of missing values in tables.

Language:JavaScriptApache-2.047300

rerope

Rectified Rotary Position Embeddings

Language:Python31800

outlines

Structured Text Generation

Language:PythonApache-2.0679200

lmql

A language for constraint-guided and efficient LLM programming.

Language:PythonApache-2.0345600

guidance

A guidance language for controlling large language models.

Language:Jupyter NotebookMIT1803700

DeepSpeed-MII

MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.

Language:PythonApache-2.0173700

hf-hub-ctranslate2

Connecting Transformers on HuggingFace Hub with CTranslate2

Language:PythonMIT3000

text-generation-inference

Large Language Model Text Generation Inference

Language:PythonApache-2.0827700

ctransformers

Python bindings for the Transformer models implemented in C/C++ using GGML library.

Language:CMIT174800