xwjim Goto Github PK

agentgpt

🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.

autogen

Enable Next-Gen Large Language Model Applications. Join our Discord: https://discord.gg/pAbnFJrkgZ

bang

BANG is a new pretraining model to Bridge the gap between Autoregressive (AR) and Non-autoregressive (NAR) Generation. AR and NAR generation can be uniformly regarded as to what extent previous tokens can be attended, and BANG bridges AR and NAR generation by designing a novel model structure for large-scale pretraining. The pretrained BANG model can simultaneously support AR, NAR and semi-NAR generation to meet different requirements.

chatglm2-6b

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

copyisallyouneed

Codebase for Copy-Generator model, including an implementation of kNN-LM

data-copilot

Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow

deepspeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

docre-rec

This repository is the PyTorch implementation of our DocRE model with reconstruction in AAAI 2021 Paper "Document-Level Relation Extraction with Reconstruction".

drn

PyTorch implementation for ACL-IJCNLP 2021 Findings paper: Discriminative Reasoning for Document-level Relation Extraction

eagle

EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

easyedit

An Easy-to-use Knowledge Editing Framework for LLMs.

evals

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

fireact

FireAct: Toward Language Agent Fine-tuning

kenlm

KenLM: Faster and Smaller Language Model Queries

llama-factory

Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)

llama-x

Open Academic Research on Improving LLaMA to SOTA LLM

lmflow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Model for All.

lookaheaddecoding

medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

megatron-deepspeed

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

megatron-llm

distributed trainer for LLMs

metagpt

🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo

mnbvc

MNBVC(Massive Never-ending BT Vast Chinese corpus)超大规模中文语料集。对标chatGPT训练的40T数据。MNBVC数据集不但包括主流文化，也包括各个小众文化甚至火星文的数据。MNBVC数据集包括新闻、作文、小说、书籍、杂志、论文、台词、帖子、wiki、古诗、歌词、商品介绍、笑话、糗事、聊天记录等一切形式的纯文本中文数据。

modelscope-agent

ModelScope-Agent: An agent framework connecting models in ModelScope with the world

modelzoo

naus

Official implementation of the ACL 2022 paper "Learning Non-Autoregressive Models from Search for Unsupervised Sentence Summarization"

ouroboros

Ouroboros: Speculative Decoding with Large Model Enhanced Drafting

painlessinferenceacceleration

rrhf

RRHF & Wombat

sequoia

scalable and robust tree-based speculative decoding algorithm