Lincoln Gachagua's picture

Lincoln Gachagua

Presidentlin

·

AI & ML interests

None yet

Recent Activity

upvoted a collection about 3 hours ago

PaliGemma 2 Mix

liked a model about 3 hours ago

microsoft/wham

liked a Space about 3 hours ago

stepfun-ai/Step-Audio

View all activity

Organizations

None yet

Presidentlin's activity

upvoted a collection about 3 hours ago

PaliGemma 2 Mix

13 items • Updated about 3 hours ago • 13

upvoted 3 papers 1 day ago

DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior

Paper • 2310.16818 • Published Oct 25, 2023 • 32

Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling

Paper • 2501.17811 • Published 21 days ago • 5

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

Paper • 2502.11089 • Published 3 days ago • 108

upvoted a collection 1 day ago

SkyReels-V1

SkyReels V1 open models collections • 2 items • Updated 2 days ago • 12

upvoted 2 collections 2 days ago

Llasa

TTS foundation model compatible with Llama framework (160k hours tokenized speech data released) • 11 items • Updated 6 days ago • 6

Step-Audio

Step-Audio model family, including Audio-Tokenizer, Audio-Chat and TTS • 3 items • Updated 2 days ago • 20

upvoted a collection 7 days ago

Nomic Embed v2

Multilingual Embedding Models • 4 items • Updated 4 days ago • 11

upvoted 2 collections 8 days ago

OLMoE (January 2025)

Improved OLMoE for iOS app. Read more: https://allenai.org/blog/olmoe-app • 10 items • Updated 8 days ago • 9

Ovis2

Our latest advancement in multi-modal large language models (MLLMs) • 8 items • Updated 3 days ago • 38

upvoted a collection 9 days ago

OREAL

7 items • Updated 9 days ago • 6

upvoted 3 collections 13 days ago

Granite Experiments

Experimental projects under consideration for the Granite family. • 6 items • Updated 33 minutes ago • 9

Hibiki fr-en

Hibiki is a model for streaming speech translation , which can run on device! See https://github.com/kyutai-labs/hibiki. • 5 items • Updated 13 days ago • 48

QLIP

QLIP is a family of image tokenizers with SOTA reconstruction quality and zero-shot image understanding. • 3 items • Updated 13 days ago • 7

upvoted a collection 14 days ago

Xwen-Chat

6 items • Updated 16 days ago • 12

upvoted a collection 18 days ago

Tulu 3 Models

All models released with Tulu 3 -- state of the art open post-training recipes. • 11 items • Updated 7 days ago • 90

upvoted a collection 20 days ago

TinySwallow

Compact Japanese models trained with "TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models" • 5 items • Updated 21 days ago • 16

upvoted a collection 21 days ago

YuE

YuE is a groundbreaking series of open-source foundation models designed for music generation, led by HKUST. • 7 items • Updated 21 days ago • 2

upvoted an article 22 days ago

Article

Welcome to Inference Providers on the Hub 🔥

23 days ago

• 378

upvoted a collection 24 days ago

Qwen2.5-1M

The long-context version of Qwen2.5, supporting 1M-token context lengths • 2 items • Updated 24 days ago • 100