Models
Datasets
Spaces
Buckets new
Docs
Enterprise
Pricing
- Website
- Community
- Solutions
Log In
Sign Up

Collections

Discover the best community collections!

Collections trending this week

Explainable deepfake detection

EfficientNet-B4 deepfake detectors with Grad-CAM facial-region analysis on FaceForensics++, and the papers they build on.

mertkayacs/xdfdet

Video Classification • Updated 1 day ago • 698 • 1
FaceForensics++: Learning to Detect Manipulated Facial Images

Paper • 1901.08971 • Published Jan 25, 2019 • 1
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

Paper • 1905.11946 • Published May 28, 2019 • 4
Improved Regularization of Convolutional Neural Networks with Cutout

Paper • 1708.04552 • Published Aug 15, 2017

Final V2-gt2 models and datasets. Intermediate checkpoints are in Wonda (Models) and Wonda (Datasets).

idopinto/Wonda-Qwen3-14B-nt-V2-gt2-e3

Text Generation • 15B • Updated Jun 21 • 19
idopinto/Wonda-Qwen3-8B-nt-V2-gt2-LoRA-e2

Updated Jan 19
idopinto/Wonda-Llama3.1-8B-Instruct-V2-gt2-e3

Text Generation • 8B • Updated Jun 21 • 23
idopinto/Wonda-Mistral-7B-Instruct-v0.3-V2-gt2-e3

Text Generation • 7B • Updated May 18 • 25

openai/whisper-tiny

Automatic Speech Recognition • 37.8M • Updated Feb 29, 2024 • 948k • 453

msc-smart-contract-auditing/vulnerability-severity-classification

Viewer • Updated May 4, 2024 • 2.91k • 150 • 3
Manirathinam21/Resume_classification

Viewer • Updated Mar 9, 2024 • 2.47k • 14
AlexanderHolmes0/true-fake-news

Viewer • Updated Apr 12, 2024 • 44.9k • 24
WNT3D/Ultimate-Offensive-Red-Team

Viewer • Updated Aug 23, 2025 • 25.6k • 781 • 164

GR00T N1.7 Panda bread_toast

GR00T N1.7 on bread_toast_part_1, relrot EE. B=128 (4k/8k/12k) and B=8 (21k/42k/63k).

PANDA-HSP/groot17-panda-ee-bread_toast_b128_relrot_4k

Robotics • 3B • Updated 2 days ago • 17
PANDA-HSP/groot17-panda-ee-bread_toast_b128_relrot_8k

Robotics • 3B • Updated 2 days ago • 12
PANDA-HSP/groot17-panda-ee-bread_toast_b128_relrot

Robotics • 3B • Updated 2 days ago • 8
PANDA-HSP/groot17-panda-ee-bread_toast_b8_relrot_21k

Robotics • 3B • Updated 2 days ago • 12

Open benchmarks

Test sets with recorded results: JevAlt decision models in three languages and Tholos-Bench for local tool-use agents.

mertkayacs/jevalt-bench

Viewer • Updated 1 day ago • 3.12k • 1.39k • 1
mertkayacs/tholos-bench

Viewer • Updated 1 day ago • 160 • 74

akatz-ai/MiniMax-H3-Character-Swap-LoRA

Video-to-Video • Updated about 21 hours ago • 36.2k • 398

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated Aug 14 • 6.77M • • 17.4k

OmniVoice TTS - Macedonian fine-tunes

OmniVoice fine-tuned for Macedonian TTS: 7 LoRA + 1 full. Notes: pronunciation CER, UTMOS, speaker sim on 68 holdout clips.

k2-fsa/OmniVoice

Text-to-Speech • 0.6B • Updated Jul 3 • 1.46M • 1.5k
h-gajdov/omnivoice-mk-all-lora-r32-lr2e-4

Text-to-Speech • Updated 2 days ago • 3
h-gajdov/omnivoice-mk-all-lora-r16-lr1e-4

Text-to-Speech • Updated 2 days ago • 3
h-gajdov/omnivoice-mk-all-lora-r32-lr1e-4

Text-to-Speech • Updated 2 days ago • 2

DGX Spark Best Model s

nvidia/Qwen3.8-Flash-Next-NVFP4

Image-Text-to-Text • 120B • Updated Sep 5 • 346k • 364
nvidia/Qwen3.8-27B-NVFP4

Text Generation • 18B • Updated 23 days ago • 622k • 179
abenzerps/Qwen-Image-2.1-Uncensored-GGUF

Text-to-Image • 7B • Updated 13 days ago • 2.1M • 3.89k
MiniMaxAI/MiniMax-H3

Image-Text-to-Video • 33B • Updated Aug 13 • 3.6M • • 6.03k

Explainable deepfake detection

EfficientNet-B4 deepfake detectors with Grad-CAM facial-region analysis on FaceForensics++, and the papers they build on.

mertkayacs/xdfdet

Video Classification • Updated 1 day ago • 698 • 1
FaceForensics++: Learning to Detect Manipulated Facial Images

Paper • 1901.08971 • Published Jan 25, 2019 • 1
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

Paper • 1905.11946 • Published May 28, 2019 • 4
Improved Regularization of Convolutional Neural Networks with Cutout

Paper • 1708.04552 • Published Aug 15, 2017

Open benchmarks

Test sets with recorded results: JevAlt decision models in three languages and Tholos-Bench for local tool-use agents.

mertkayacs/jevalt-bench

Viewer • Updated 1 day ago • 3.12k • 1.39k • 1
mertkayacs/tholos-bench

Viewer • Updated 1 day ago • 160 • 74

Final V2-gt2 models and datasets. Intermediate checkpoints are in Wonda (Models) and Wonda (Datasets).

idopinto/Wonda-Qwen3-14B-nt-V2-gt2-e3

Text Generation • 15B • Updated Jun 21 • 19
idopinto/Wonda-Qwen3-8B-nt-V2-gt2-LoRA-e2

Updated Jan 19
idopinto/Wonda-Llama3.1-8B-Instruct-V2-gt2-e3

Text Generation • 8B • Updated Jun 21 • 23
idopinto/Wonda-Mistral-7B-Instruct-v0.3-V2-gt2-e3

Text Generation • 7B • Updated May 18 • 25

akatz-ai/MiniMax-H3-Character-Swap-LoRA

Video-to-Video • Updated about 21 hours ago • 36.2k • 398

openai/whisper-tiny

Automatic Speech Recognition • 37.8M • Updated Feb 29, 2024 • 948k • 453

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated Aug 14 • 6.77M • • 17.4k

msc-smart-contract-auditing/vulnerability-severity-classification

Viewer • Updated May 4, 2024 • 2.91k • 150 • 3
Manirathinam21/Resume_classification

Viewer • Updated Mar 9, 2024 • 2.47k • 14
AlexanderHolmes0/true-fake-news

Viewer • Updated Apr 12, 2024 • 44.9k • 24
WNT3D/Ultimate-Offensive-Red-Team

Viewer • Updated Aug 23, 2025 • 25.6k • 781 • 164

OmniVoice TTS - Macedonian fine-tunes

OmniVoice fine-tuned for Macedonian TTS: 7 LoRA + 1 full. Notes: pronunciation CER, UTMOS, speaker sim on 68 holdout clips.

k2-fsa/OmniVoice

Text-to-Speech • 0.6B • Updated Jul 3 • 1.46M • 1.5k
h-gajdov/omnivoice-mk-all-lora-r32-lr2e-4

Text-to-Speech • Updated 2 days ago • 3
h-gajdov/omnivoice-mk-all-lora-r16-lr1e-4

Text-to-Speech • Updated 2 days ago • 3
h-gajdov/omnivoice-mk-all-lora-r32-lr1e-4

Text-to-Speech • Updated 2 days ago • 2

GR00T N1.7 Panda bread_toast

GR00T N1.7 on bread_toast_part_1, relrot EE. B=128 (4k/8k/12k) and B=8 (21k/42k/63k).

PANDA-HSP/groot17-panda-ee-bread_toast_b128_relrot_4k

Robotics • 3B • Updated 2 days ago • 17
PANDA-HSP/groot17-panda-ee-bread_toast_b128_relrot_8k

Robotics • 3B • Updated 2 days ago • 12
PANDA-HSP/groot17-panda-ee-bread_toast_b128_relrot

Robotics • 3B • Updated 2 days ago • 8
PANDA-HSP/groot17-panda-ee-bread_toast_b8_relrot_21k

Robotics • 3B • Updated 2 days ago • 12

DGX Spark Best Model s

nvidia/Qwen3.8-Flash-Next-NVFP4

Image-Text-to-Text • 120B • Updated Sep 5 • 346k • 364
nvidia/Qwen3.8-27B-NVFP4

Text Generation • 18B • Updated 23 days ago • 622k • 179
abenzerps/Qwen-Image-2.1-Uncensored-GGUF

Text-to-Image • 7B • Updated 13 days ago • 2.1M • 3.89k
MiniMaxAI/MiniMax-H3

Image-Text-to-Video • 33B • Updated Aug 13 • 3.6M • • 6.03k

Previous
1
...
104
105
106
107
108
...
23,879
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs