Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up

Collections

Discover the best community collections!

Collections trending this week

End-to-End Omni (text, audio, image, video, and natural speech interaction) model based Qwen2.5

Qwen/Qwen2.5-Omni-7B

Any-to-Any • Updated about 2 hours ago • 16.3k • 716
Running

140

140

Qwen2.5 Omni 7B Demo

🏆

Submit media inputs to generate text and speech responses
Qwen2.5-Omni Technical Report

Paper • 2503.20215 • Published 3 days ago • 88

💫StarVector Models

StarVector is a multimodal LLM for Scalable Vector Graphics (SVG) generation, producing structured SVG code directly from images and text.

starvector/starvector-1b-im2svg

Text Generation • Updated 9 days ago • 11.9k • 133
starvector/starvector-8b-im2svg

Text Generation • Updated 9 days ago • 6.24k • 354

deepseek-ai/DeepSeek-V3-Base

Updated 1 day ago • 307k • 1.61k
deepseek-ai/DeepSeek-V3

Text Generation • Updated 1 day ago • 1.42M • • 3.74k
DeepSeek-V3 Technical Report

Paper • 2412.19437 • Published Dec 27, 2024 • 56
deepseek-ai/DeepSeek-V3-0324

Text Generation • Updated 1 day ago • 47.6k • • 1.91k

TxGemma Release

Collection of open models to accelerate the development of therapeutics.

google/txgemma-2b-predict

Text Generation • Updated 3 days ago • 424 • 15
google/txgemma-9b-predict

Text Generation • Updated 3 days ago • 65 • 9
google/txgemma-9b-chat

Text Generation • Updated 3 days ago • 148 • 16
google/txgemma-27b-predict

Text Generation • Updated 3 days ago • 244 • 13

Gemma 3 Release

google/gemma-3-4b-it

Image-Text-to-Text • Updated 7 days ago • 326k • 357
google/gemma-3-4b-pt

Image-Text-to-Text • Updated 7 days ago • 27.9k • 54
google/gemma-3-1b-pt

Text Generation • Updated 7 days ago • 58.4k • 93
google/gemma-3-1b-it

Text Generation • Updated 7 days ago • 290k • 235

Vision-language model series based on Qwen2.5

Running

56

56

Qwen2.5 VL 32B Instruct Demo

🏃

Chat with images and videos using Qwen
Running

195

195

Qwen2.5 VL 72B Instruct

💻

Interact with Qwen2.5-VL-Chat model using text and files
Qwen2.5-VL Technical Report

Paper • 2502.13923 • Published Feb 19 • 175
Qwen/Qwen2.5-VL-32B-Instruct

Image-Text-to-Text • Updated 2 days ago • 72.7k • 246

MoshiVis is a Vision Speech Model built as a perceptually-augmented version of Moshi v0.1 for conversing about image inputs

kyutai/Babillage

Viewer • Updated 7 days ago • 465k • 122 • 6
kyutai/moshika-vis-pytorch-bf16

Updated 6 days ago • 50
kyutai/moshika-vis-candle-bf16

Updated 10 days ago
kyutai/moshika-vis-candle-q8

Updated 10 days ago • 8.3k

MambaVision: A Hybrid Mamba-Transformer Vision Backbone. Includes both 1K and 21K pretrained models.

nvidia/MambaVision-L3-512-21K

Image Classification • Updated about 23 hours ago • 322 • 34
nvidia/MambaVision-L3-256-21K

Image Classification • Updated about 23 hours ago • 46 • 7
nvidia/MambaVision-L2-512-21K

Image Classification • Updated about 23 hours ago • 30 • 3
nvidia/MambaVision-L-21K

Image Classification • Updated about 23 hours ago • 42 • 4

Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ

Running on L4

58

58

DeTikZify

📈

Convert images and sketches into graphics programs with TikZ
DeTikZify: Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ

Paper • 2405.15306 • Published May 24, 2024 • 7
nllg/detikzify-v2-8b

Text2Text Generation • Updated 11 days ago • 397 • 9
nllg/detikzify-ds-7b

Text Generation • Updated Dec 4, 2024 • 274 • 5

SuperBPE tokenizers and models trained with them

SuperBPE: Space Travel for Language Models

Paper • 2503.13423 • Published 11 days ago • 9
UW/OLMo2-8B-SuperBPE-t180k

Text Generation • Updated 9 days ago • 129 • 6
UW/OLMo2-11B-SuperBPE-t180k

Text Generation • Updated 9 days ago • 20 • 2
UW/OLMo2-8B-SuperBPE-t160k

Text Generation • Updated 9 days ago • 19 • 2

Previous
1
2
3
...
10,602
Next

Company

TOS Privacy About Jobs

Website

Models Datasets Spaces Pricing Docs