ftgreat Goto Github PK

moss-rlhf

MOSS-RLHF

ms-amp

Microsoft Automatic Mixed Precision Library

mup

maximal update parametrization (µP)

mutransformers

some common Huggingface transformers in maximal update parametrization (µP)

nbce

Naive Bayes-based Context Extension

nemo

NeMo: a toolkit for conversational AI

nemo-megatron-launcher

NeMo Megatron launcher and tools

nlp_chinese_corpus

大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP

nvtop

GPUs process monitoring for AMD, Intel and NVIDIA

open-llama

The complete training code of the open-source high-performance Llama model, including the full process from pre-training to RLHF.

open_llama

openagents

OpenAgents: An Open Platform for Language Agents in the Wild

openchat

OpenChat: Advancing Open-source Language Models with Imperfect Data

openchatkit

openllama2

A Ray-based High-performance LLaMA2 RLHF framework

pai-megatron-patch

palm-rlhf-pytorch

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

pandallm

Panda: 海外中文开源大语言模型，基于 Llama-7B, -13B, -33B, -65B 进行中文领域上的持续预训练。

qwen-agent

Agent framework and applications built upon Qwen, featuring Code Interpreter and Chrome browser extension.

ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

resume

s4

Structured state space sequence models

science-llm

A large-scale language model for scientific domain, trained on redpajama arXiv split

simctg

[NeurIPS'22 Spotlight] A Contrastive Framework for Neural Text Generation

skywork

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

t5-pegasus

中文生成式预训练模型

tensorrt-llm

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 efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

text-generation-inference

Large Language Model Text Generation Inference

training-code

The code we currently use to fine-tune models.