🤱🏻 Turn any webpage into a desktop app with one command.

[ICLR 2025] <MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses>

AI powered local typing assistant built with Ollama

Use pytorch profile api to further analysis the training detailed information, like heaps and stacks, time consuming.

The official evaluation suite and dynamic data release for MixEval.

Custom CSS Plugin for Visual Studio Code. Based on vscode-icon

Open-Sora: Democratizing Efficient Video Production for All

SpeeD: A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training

🙌 OpenHands: AI-Driven Development

Byted PyTorch Distributed for Hyperscale Training of LLMs and RLs

Lossless Training Speed Up by Unbiased Dynamic Data Pruning

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

This repository contains code to quantitatively evaluate instruction-tuned models such as Alpaca and Flan-T5 on held-out tasks.

A family of open-sourced Mixture-of-Experts (MoE) Large Language Models

[ICCV2023] Dataset Quantization

A framework for few-shot evaluation of language models.

Reference implementation for DPO (Direct Preference Optimization)

Efficient Dataset Distillation by Representative Matching

Inference code for Llama models

Inconsistencies in Masked Language Models

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

Making large AI models cheaper, faster and more accessible

Repository for ACL 2022 paper Mix and Match: Learning-free Controllable Text Generation using Energy Language Models

GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)

Thesis Latex Template for Nanyang Technological University (NTU)

FusedChat is a dialogue dataset. It contains dialogue sessions fusing task-oriented dialogues and open-domain dialogues.

Unified MultiWOZ evaluation scripts for the context-to-response task.

DSTC8 Track 1 Task 1 End-to-End Multi-Domain Dialog Challenge Result:

PyTorch code for ICLR 2019 paper: Global-to-local Memory Pointer Networks for Task-Oriented Dialogue https://arxiv.org/pdf/1901.04713