Haowen Hou's repositories
VisualRWKV
VisualRWKV is the visual-enhanced version of the RWKV language model, enabling RWKV to handle various visual tasks.
transformers-benchmarks-exercise
exercise for transformers-benchmarks, add 3090 benchmark
UniqueClassCount
Pytorch implementation for ICLR 2020 paper "Weakly Supervised Clustering by Exploiting Unique Class Count"
cc_net-update
Tools to download and cleanup Common Crawl data, updated to 2023
Language:Jupyter NotebookApache-2.0000
json2binidx_tool
update to support RUST RWKV Tokenizer
Language:Python000
LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
Language:PythonApache-2.0000
Visual-MQAR
Understand and test multi-modal language model architectures on Visual-MQAR task.
VQASynth
Compose multimodal datasets 🎹
Language:Python000