Takumi Okoshi

takuoko's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection 10 days ago

SFTvsRL Models & Data

Collection

This collection contains 4 initial checkpoints for https://github.com/LeslieTrue/SFTvsRL and necessary data for V-IRL training. • 5 items • Updated 7 days ago • 7

upvoted a collection 13 days ago

Eagle 2

Collection

Eagle 2 is a family of frontier vision-language models with vision-centric design. The model supports 4K HD input, long-context video, and grounding. • 9 items • Updated 20 days ago • 31

upvoted a collection 9 months ago

Mantis

Collection

Mantis model family optimized for multi-image reasoning with interleaved text/image format • 11 items • Updated Jul 2, 2024 • 9

upvoted a collection 10 months ago

Pile-T5

Collection

T5 trained on the Pile with Llama Tokenizer • 4 items • Updated Jul 6, 2024 • 17

upvoted a collection 11 months ago

MGM

Collection

Official model collection for the paper "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models" • 13 items • Updated May 3, 2024 • 47