Running large language models on a single GPU for throughput-oriented scenarios.
-
Updated
Apr 19, 2024 - Python
Running large language models on a single GPU for throughput-oriented scenarios.
A crowdsourced distributed cluster for AI art and text generation
New OTP Bot, working with any company or service name to fetch otp code.
Train very large language models in Jax.
MinT: Minimal Transformer Library and Tutorials
Curated list of open source and openly accessible large language models
This is the official PyTorch implementation of "LLM-QBench: A Benchmark Towards the Best Practice for Post-training Quantization of Large Language Models", and also an efficient LLM compression tool with various advanced compression methods, supporting multiple inference backends.
Config files for my GitHub profile.
Repositorio dedicado para nuestro proyecto de estructuras computacionales. albergando todos los algoritmos requeridos
Small benchmark library focused on avoiding optimization/deoptimization pollution between tests by isolating them.
4D reconstruction of developmental trajectories using spherical harmonics
XenTrace data processing interface for KernelShark.
This bot attends the online classes held on Microsoft teams, according to the given timetable.Informs if bot is successfully joined the meeting through discord.
Adds (up to date) TweakScale /L patches for Orbit Portal Technologies (OPT).
Training and inference scripts for Meta's OPT LLM models using the Alpaca Instruct format.
Add a description, image, and links to the opt topic page so that developers can more easily learn about it.
To associate your repository with the opt topic, visit your repo's landing page and select "manage topics."