Juyoung Suk's repositories
alignment-handbook
Robust recipes for to align language models with human and AI preferences
frontend-study
Study about Web and Frontend
cheatsheet
Collection of commands that I use often
AgentBench
A Comprehensive Benchmark to Evaluate LLMs as Agents
autotab-starter
Build browser agents for real world tasks
axolotl
Go ahead and axolotl questions
calendar
Enhancing large language models (LLMs) temporal reasoning ability with calendar use.
Dockerfiles
My Dockerfiles for research
easy-lm-trainer
🤗 최소한의 세팅으로 LM을 학습하기 위한 샘플코드
Instructdial
Code for the paper Code for the paper InstructDial: Improving Zero and Few-shot Generalization in Dialogue through Instruction Tuning
JudgeLM
An open-sourced LLM judge for evaluating LLM-generated answers.
kotoba-recipes
Support Continual pre-training & Instruction Tuning forked from llama-recipes
LLaMA-Factory
Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)
llama_index
LlamaIndex (GPT Index) is a project that provides a central interface to connect your LLM's with external data.
Mantis
Official code for Paper "Mantis: Multi-Image Instruction Tuning"
Mind2Web
Dataset, code and models for the paper "Mind2Web: Towards a Generalist Agent for the Web".
OpenAgents
OpenAgents: An Open Platform for Language Agents in the Wild
prometheus
[ICLR 2024 & NeurIPS 2023 WS] An Evaluator LM that is open-source, offers reproducible evaluation, and inexpensive to use. Specifically designed for fine-grained evaluation on a customized score rubric, Prometheus is a good alternative for human evaluation and GPT-4 evaluation.
scottsuk0306
Github Profile
storm
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
transformer-from-scratch
Unofficial Implementation of Transformers
webarena
Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"
zero123
Zero-1-to-3: Zero-shot One Image to 3D Object: https://zero123.cs.columbia.edu/