Dongfu Jiang's Projects
Instruct-tune LLaMA on consumer hardware
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
This repo contains evaluation code for the paper "BLINK: Multimodal Large Language Models Can See but Not Perceive". https://arxiv.org/abs/2404.12390
š³ bore is a simple CLI tool for making tunnels to localhost
A Neural Framework for MT Evaluation
Fusion-in-Decoder
gradio multimodalchatbot from gradio docs
My streamlit deploy attempt
my homepage
My Personal Progfile readme file
A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
[NeurIPS'23 Oral] Visual Instruction Tuning: LLaVA (Large Language-and-Vision Assistant) built towards GPT-4V level capabilities.
A simple generate script utils using fastchat conv template for generation of Large Language Models
Accelerating the development of large multimodal models (LMMs) with lmms-eval
Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes
Poker games as an OOP project
š¦¦ Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
RewardBench: the first evaluation tool for reward models.
Html visualization for the spacy dependency parsing using brat
Repository for EMNLP 2022 Paper: Towards a Unified Multi-Dimensional Evaluator for Text Generation
Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
A high-throughput and memory-efficient inference and serving engine for LLMs