Qwen2.5-VL Collection Vision-language model series based on Qwen2.5 • 3 items • Updated 4 days ago • 286
Qwen2.5-1M Collection The long-context version of Qwen2.5, supporting 1M-token context lengths • 2 items • Updated 4 days ago • 87
ViTPose Collection Collection for ViTPose models based on transformers implementation. • 10 items • Updated 18 days ago • 12
KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model Paper • 2501.01028 • Published 29 days ago • 13
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 7 days ago • 27
Llama 3.3 Collection This collection hosts the transformers and original repos of the Llama 3.3 • 1 item • Updated Dec 6, 2024 • 124
PaliGemma 2 Release Collection Vision-Language Models available in multiple 3B, 10B and 28B variants. • 23 items • Updated Dec 13, 2024 • 133
SmolVLM Collection State-of-the-art compact VLMs for on-device applications: Base, Synthetic, and Instruct • 5 items • Updated Dec 22, 2024 • 32
Arabic Matryoshka Embedding Models Collection A collection of advanced Arabic Matryoshka Embedding Models designed for efficient and high-performance Arabic NLP, available publicly on Hugging Face • 10 items • Updated Dec 4, 2024 • 10
GATE: General Arabic Text Embedding Models Collection This Collection includes GATE Models, a new series of trained sentence transformer models trained on multi-task datasets and using different losses. • 2 items • Updated Aug 29, 2024 • 1
AIMv2 Collection A collection of AIMv2 vision encoders that supports a number of resolutions, native resolution, and a distilled checkpoint. • 19 items • Updated Nov 22, 2024 • 71
jina-embeddings-v3 Collection Multilingual multi-task general text embedding model • 6 items • Updated Sep 19, 2024 • 20
SmolLM2 Collection State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 15 items • Updated Dec 22, 2024 • 208
AMD-OLMo Collection AMD-OLMo are a series of 1 billion parameter language models trained by AMD on AMD Instinct™ MI250 GPUs based on OLMo. • 4 items • Updated Oct 31, 2024 • 18