Pinned Repositories
chameleon
Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.
awesome-storytelling
iz2late.github.io
vanilla-seq2seq
A lightweight, minimal pytorch's sequence-to-sequence(seq2seq) model, with the newest torchtext 0.8.0(from 2020), which can serve as seq2seq baseline in your research.
VIST-Character
Otter
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.
zerommt
3AM
Official code and data of "3AM: An Ambiguity-Aware Multi-Modal Machine Translation Dataset"
straplines
SoM-LLaVA
[COLM-2024] List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs
iz2late's Repositories
iz2late/VIST-Character
iz2late/awesome-storytelling
iz2late/vanilla-seq2seq
A lightweight, minimal pytorch's sequence-to-sequence(seq2seq) model, with the newest torchtext 0.8.0(from 2020), which can serve as seq2seq baseline in your research.
iz2late/iz2late.github.io