petitetech Goto Github PK

composio

Composio equips agents with well-crafted tools empowering them to tackle complex tasks

cosmopedia

data-juicer

A one-stop data processing system to make data higher-quality, juicier, and more digestible for LLMs! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大语言模型提供更高质量、更丰富、更易”消化“的数据！

datatrove

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

dclm

DataComp for Language Models

deepseek-v2

dlrover

DLRover: An Automatic Distributed Deep Learning System

glm-4

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

internevo

leaderboard

SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.

llama3

The official Meta Llama 3 GitHub site

llm-swarm

Manage scalable open LLM inference endpoints in Slurm clusters

megalodon

Reference implementation of Megalodon 7B model

megatron-deepspeed

Ongoing research training transformer language models at scale, including: BERT & GPT-2

mixinglaws

moa

mu_transformer

Transformer with Mu-Parameterization, implemented in Jax/Flax. Supports FSDP on TPU pods.

mup

maximal update parametrization (µP)

mutransformers

some common Huggingface transformers in maximal update parametrization (µP)

nanotron

Minimalistic large language model 3D-parallelism training

nemo

NeMo: a framework for generative AI

nemo-aligner

Scalable toolkit for efficient model alignment

open-sora

Open-Sora: Democratizing Efficient Video Production for All

pipecat

Open Source framework for voice and multimodal conversational AI

prompt2model

prompt2model - Generate Deployable Models from Natural Language Instructions

pruneme

Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models

qwen-audio

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

recognize-anything

Open-source and strong foundation image recognition models.

self-llm

《开源大模型食用指南》基于Linux环境快速部署开源大模型，更适合**宝宝的部署教程

self-rewarding-lm-pytorch

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI