lorrinwww Goto Github PK

advertorch

A Toolbox for Adversarial Robustness Research

chatgpt-next-web

A cross-platform ChatGPT/Gemini UI (Web / PWA / Linux / Win / MacOS). 一键拥有你自己的跨平台 ChatGPT/Gemini 应用。

common-dockers

deeperspeed

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

eventextraction

fastchat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and FastChat-T5.

fmengine-torch

FMEngine [PyTorch version]

glm-130b

GLM-130B: An Open Bilingual Pre-Trained Model

gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

gpt-neox-llama

helm

Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110).

icetk

A unified tokenization tool for Images, Chinese and English.

json-stream

Simple streaming JSON parser and encoder.

lm-evaluation-harness

A framework for few-shot evaluation of autoregressive language models.

lm-format-enforcer

Enforce the output format (JSON Schema, Regex etc) of a language model

lorrinwww.github.io

Jue's blog

min-dalle

min(DALL·E) is a fast, minimal port of DALL·E Mega to PyTorch

naive-rank-server

natural-instructions

Expanding natural instructions

open-instruction-generalist

Open Instruction Generalist is an assistant trained on massive synthetic instructions to perform many millions of tasks

open_clip

An open source implementation of CLIP.

openchatkit

pyramid

Code associated with the paper **Pyramid: A Layered Model for Nested Named Entity Recognition**, at ACL 2020

quick_deployment_helm

redpajama-data

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

scaled-rope

Lora

scholar-md

skipbert

Code associated with the paper **SkipBERT: Efficient Inference with Shallow Layer Skipping**, at ACL 2022

snapshot

Code associated with the paper Effective Continual Learning for Text Classification with Lightweight Snapshots, at AAAI 2023

tweetextraction