Universal LLM Deployment Engine with ML Compilation

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Transformer related optimization, including BERT, GPT

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…

Effective LLM Alignment Toolkit

🥪🦘 An open source sandbox project exploring dbt workflows via a fictional sandwich shop's data.

A self-contained dbt project for testing purposes

Hugging Face Inference Toolkit used to serve transformers, sentence-transformers, and diffusers models.

A fork of vLLM with Hugging Face specific modifications

Examples of programs built using Modal

Provide a way to use the GPT-QLLama model as an API

GPTQLoRA: Efficient Finetuning of Quantized LLMs with GPTQ

Neural Machine Translation using a Transformer model (T5)

This repository demonstrates how to fine-tune the Google Gemma 2 2B model to improve its performance on Japanese instruction-following tasks. It serves as a practical guide for developers and resea…

GGUF Quantization of any LLM.

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

The open source implementation of Gemini, the model that will "eclipse ChatGPT" by Google

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

✨ Magical shell history

Declarative CLI Version manager written in Go. Support Lazy Install, Registry, and continuous update with Renovate. CLI version is switched seamlessly

日本語LLMまとめ - Overview of Japanese LLMs

Example application for the task of fine-tuning pretrained machine translation models on highly domain-specific, self-extracted translated sentences

All-in-one repo to deploy an automated pipeline for GCP Cloud assets inventory and visualise with Looker studio

Proof of Concept for to get data from Cloud Asset Inventory and send to BigQuery

Zero-Inflated Gamma probabilistic model

Upgrading Istio with 0 downtime