howard-hou

Haowen Hou's repositories

VisualRWKV is the visual-enhanced version of the RWKV language model, enabling RWKV to handle various visual tasks.

Language:PythonApache-2.0164 3 5

PyTorch code for BagFormer: Better Cross-Modal Retrieval via bag-wise interaction

Language:Python113 300

RWKV-TS: Beyond Traditional Recurrent Neural Network for Time Series Tasks

Language:Python62 2 4

exercise for transformers-benchmarks, add 3090 benchmark

Language:Jupyter NotebookApache-2.0800

Pytorch implementation for ICLR 2020 paper "Weakly Supervised Clustering by Exploiting Unique Class Count"

Language:Jupyter NotebookMIT7 10

Tools to download and cleanup Common Crawl data, updated to 2023

Language:PythonMIT300

Language:Jupyter NotebookApache-2.0000

update to support RUST RWKV Tokenizer

Language:Python000

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Language:PythonApache-2.0000

Understand and test multi-modal language model architectures on Visual-MQAR task.

Language:PythonApache-2.0010

Compose multimodal datasets 🎹

Language:Python000