Zinan Lin (fjxmlzn)

fjxmlzn

Geek Repo

Company:Microsoft Research

Location:Redmond, Washington, US

Home Page:https://zinanlin.me

Twitter:@lin_zinan

Github PK Tool:Github PK Tool


Organizations
fanti-lab
netsharecmu
projectdatafuel

Zinan Lin's starred repositories

semantic-kernel

Integrate cutting-edge LLM technology quickly and easily into your apps

consistency_models

Official repo for consistency models.

Language:PythonLicense:MITStargazers:5978Issues:59Issues:49

agents

An Open-source Framework for Autonomous Language Agents

Language:PythonLicense:Apache-2.0Stargazers:4588Issues:59Issues:68

latent-consistency-model

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

Language:PythonLicense:MITStargazers:4138Issues:62Issues:89

LLMLingua

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

Language:PythonLicense:MITStargazers:4001Issues:32Issues:97

learn2learn

A PyTorch Library for Meta-learning Research

Language:PythonLicense:MITStargazers:2557Issues:32Issues:256

chain-of-thought-hub

Benchmarking large language models' complex reasoning ability with chain-of-thought prompting

Language:Jupyter NotebookLicense:MITStargazers:2391Issues:38Issues:34

pytorch-meta

A collection of extensions and data-loaders for few-shot learning & meta-learning in PyTorch

Language:PythonLicense:MITStargazers:1942Issues:44Issues:141

Chain-of-ThoughtsPapers

A trend starts from "Chain of Thought Prompting Elicits Reasoning in Large Language Models".

helm

Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110). This framework is also used to evaluate text-to-image models in Holistic Evaluation of Text-to-Image Models (HEIM) (https://arxiv.org/abs/2311.04287).

Language:PythonLicense:Apache-2.0Stargazers:1692Issues:31Issues:1017

higher

higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

Language:PythonLicense:Apache-2.0Stargazers:1575Issues:28Issues:108

functorch

functorch is JAX-like composable function transforms for PyTorch.

Language:Jupyter NotebookLicense:BSD-3-ClauseStargazers:1376Issues:27Issues:520

docker-pytorch

A Docker image for PyTorch

Language:DockerfileLicense:MITStargazers:954Issues:23Issues:37

RectifiedFlow

Official Implementation of Rectified Flow (ICLR2023 Spotlight)

pal

PaL: Program-Aided Language Models (ICML 2023)

Language:PythonLicense:Apache-2.0Stargazers:440Issues:8Issues:12

consistency_models

Unofficial Implementation of Consistency Models in pytorch

smartnoise-sdk

Tools and service for differentially private processing of tabular and relational data

Language:PythonLicense:MITStargazers:235Issues:26Issues:229

consistency_models_cifar10

Consistency models trained on CIFAR-10, in JAX.

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:128Issues:2Issues:6

sot

[ICLR 2024] Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding

Language:PythonLicense:MITStargazers:119Issues:4Issues:0

prompt-lib

A set of utilities for running few-shot prompting experiments on large-language models

Language:PythonLicense:MITStargazers:99Issues:4Issues:6
Language:PythonLicense:MITStargazers:63Issues:2Issues:0

ClinGen

This is the code for our paper "Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language Models".

Language:PythonLicense:MITStargazers:28Issues:2Issues:0

heim

Holistic Evaluation of Text-to-Image Models (HEIM), a fork of HELM to evaluate to text-to-image models (paper coming soon).

Language:PythonLicense:Apache-2.0Stargazers:17Issues:0Issues:0
Language:PythonLicense:MITStargazers:15Issues:4Issues:0
Language:PythonStargazers:11Issues:0Issues:0
Language:PythonLicense:MITStargazers:5Issues:1Issues:0