tomyoung903

llama

Inference code for Llama models

ColossalAI

Making large AI models cheaper, faster and more accessible

OpenDevin

🐚 OpenDevin: Code Less, Make More

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

PaLM-rlhf-pytorch

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

GLM-130B

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

lm-evaluation-harness

A framework for few-shot evaluation of language models.

opencompass

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.

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

OpenMoE

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

veScale

A PyTorch Native LLM Training Framework

instruct-eval

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

InstructionWild

ConvLab

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

InfoBatch

Lossless Training Speed Up by Unbiased Dynamic Data Pruning

Dataset_Quantization

[ICCV2023] Dataset Quantization

ccm

This project is a tensorflow implement of our work, CCM (Commonsense Conversational Model).

GLMP

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

thesis_template_ntu

Thesis Latex Template for Nanyang Technological University (NTU)

SpeeD

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

DREAM

Efficient Dataset Distillation by Representative Matching

MultiWOZ_Evaluation

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

mixmatch

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

FusedChat

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

experiments

My exploration on new technologies.

MLM_inconsistencies

Inconsistencies in Masked Language Models