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

Did you lie? Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms

ai-safety-institute/lie-detection-rollouts

Updated 7 days ago • 2.49k
Lie Detection Model Organisms

Collection

Model organisms trained to reason about lying in CoT, then lie in text output. • 17 items • Updated 7 days ago
Apollo-Style Deception Probes

Collection

Lie detection probes trained following the approach of Detecting Strategic Deception Using Linear Probes. • 49 items • Updated 7 days ago
Targeted Apollo Deception Probes

Collection

Lie detection probes trained following the approach of 'Building Better Deception Probes Using Targeted Instruction Pairs' • 49 items • Updated 7 days ago

Granite 4.1 Language Models

Efficient language models for multilingual generation, coding, RAG, and AI assistant workflows.

ibm-granite/granite-4.1-30b

Text Generation • 29B • Updated May 4 • 17k • 129
ibm-granite/granite-4.1-8b

9B • Updated May 4 • 99.9k • 193
ibm-granite/granite-4.1-3b

Text Generation • 3B • Updated May 4 • 214k • 77
ibm-granite/granite-4.1-30b-base

Text Generation • 29B • Updated Apr 28 • 1.6k • 27

Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation

Paper • 2603.19220 • Published Mar 19 • 69
Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR

Paper • 2605.20164 • Published 30 days ago • 6
GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment

Paper • 2605.19577 • Published 30 days ago • 59
EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL

Paper • 2605.18703 • Published about 1 month ago • 50

LTX-2.3 base models, quantized models and accompanying LoRAs and IC-LoRAs

Lightricks/LTX-2.3

Image-to-Video • Updated Apr 13 • 1.52M • 1.39k
Lightricks/LTX-2.3-fp8

Image-to-Video • Updated Mar 16 • 729k • 109
Lightricks/LTX-2.3-nvfp4

Image-to-Video • Updated Mar 17 • 11.5k • 86
Lightricks/LTX-2.3-22b-IC-LoRA-Motion-Track-Control

Any-to-Any • Updated Apr 13 • 55

Streaming speech translation without the need for word-level alignments

Running

13

Hibiki Zero Samples

🏆

13

Demo samples of the speech translation model Hibiki-Zero.
Simultaneous Speech-to-Speech Translation Without Aligned Data

Paper • 2602.11072 • Published Feb 11 • 2
kyutai/Audio-NTREX-4L

Viewer • Updated Feb 12 • 3.6k • 744 • 5
kyutai/hibiki-zero-3b-pytorch-bf16

Audio-to-Audio • Updated Feb 12 • 2.09k • 56

DenseOn & LateOn

A collection of open state-of-the-art single and multi-vector models

lightonai/LateOn

Sentence Similarity • 0.1B • Updated 27 days ago • 6.15k • • 46
lightonai/DenseOn

Sentence Similarity • 0.1B • Updated Apr 21 • 4.59k • • 28
lightonai/LateOn-unsupervised

Sentence Similarity • 0.1B • Updated 27 days ago • 1.46k • 8
lightonai/DenseOn-unsupervised

Sentence Similarity • 0.1B • Updated Apr 21 • 24 • 8

ResearchClawBench

ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

Paper • 2606.07591 • Published 21 days ago • 90
InternScience/ResearchClawBench

Benchmark • Updated about 14 hours ago • 57 • 3.71k • 6
Running

1

ResearchHarness

🚀

1

Lightweight harness for tool-using LLM agents.
Running

Agents

ResearchClawBench Task Submission

📦

Submit and validate a ResearchClawBench task ZIP

High Quality Uncensored - GGUF on MLX

These are the empirically proven highest quality uncensored models on MLX.

dealignai/MiniMax-M2.7-JANGTQ-CRACK

Text Generation • 15B • Updated May 1 • 1.51k • 27
dealignai/Nemotron-3-Super-120B-A12B-UNCENSORED-JANG_2L

Text Generation • 13B • Updated Apr 25 • 2.81k • 11
dealignai/Gemma-4-26B-A4B-JANG_2L-CRACK

Image-Text-to-Text • 3B • Updated May 1 • 3.04k • 86
dealignai/Qwen3.5-VL-397B-A17B-UNCENSORED-JANG_1L

Image-Text-to-Text • 34B • Updated May 1 • 552 • 5

CyberSec AI Portfolio - Datasets, Models & Spaces

80+ datasets, 35 Spaces & 4 models for cybersecurity AI: RGPD, NIS2, ISO 27001, DORA, AI Act, MITRE ATT&CK & more. By Ayi NEDJIMI.

AYI-NEDJIMI/CyberSec-Assistant-3B

Text Generation • Updated Feb 21 • 12 • 2
AYI-NEDJIMI/ISO27001-Expert-1.5B

Text Generation • Updated Feb 21 • 1 • 1
AYI-NEDJIMI/RGPD-Expert-1.5B

Text Generation • Updated Feb 21 • 2 • 1
AYI-NEDJIMI/m365-expert-v3

8B • Updated Feb 18 • 8 • 1

WTF GENIUS PAPERS

Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models.

about 19 hours ago

Continuous Latent Diffusion Language Model

Paper • 2605.06548 • Published May 7 • 82
Scaling Latent Reasoning via Looped Language Models

Paper • 2510.25741 • Published Oct 29, 2025 • 231
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Paper • 2502.05171 • Published Feb 7, 2025 • 157
Pretraining Language Models to Ponder in Continuous Space

Paper • 2505.20674 • Published May 27, 2025 • 3

Did you lie? Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms

ai-safety-institute/lie-detection-rollouts

Updated 7 days ago • 2.49k
Lie Detection Model Organisms

Collection

Model organisms trained to reason about lying in CoT, then lie in text output. • 17 items • Updated 7 days ago
Apollo-Style Deception Probes

Collection

Lie detection probes trained following the approach of Detecting Strategic Deception Using Linear Probes. • 49 items • Updated 7 days ago
Targeted Apollo Deception Probes

Collection

Lie detection probes trained following the approach of 'Building Better Deception Probes Using Targeted Instruction Pairs' • 49 items • Updated 7 days ago

DenseOn & LateOn

A collection of open state-of-the-art single and multi-vector models

lightonai/LateOn

Sentence Similarity • 0.1B • Updated 27 days ago • 6.15k • • 46
lightonai/DenseOn

Sentence Similarity • 0.1B • Updated Apr 21 • 4.59k • • 28
lightonai/LateOn-unsupervised

Sentence Similarity • 0.1B • Updated 27 days ago • 1.46k • 8
lightonai/DenseOn-unsupervised

Sentence Similarity • 0.1B • Updated Apr 21 • 24 • 8

Granite 4.1 Language Models

Efficient language models for multilingual generation, coding, RAG, and AI assistant workflows.

ibm-granite/granite-4.1-30b

Text Generation • 29B • Updated May 4 • 17k • 129
ibm-granite/granite-4.1-8b

9B • Updated May 4 • 99.9k • 193
ibm-granite/granite-4.1-3b

Text Generation • 3B • Updated May 4 • 214k • 77
ibm-granite/granite-4.1-30b-base

Text Generation • 29B • Updated Apr 28 • 1.6k • 27

ResearchClawBench

ResearchClawBench: Evaluating AI Agents for Automated Research from Re-Discovery to New-Discovery

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

Paper • 2606.07591 • Published 21 days ago • 90
InternScience/ResearchClawBench

Benchmark • Updated about 14 hours ago • 57 • 3.71k • 6
Running

1

ResearchHarness

🚀

1

Lightweight harness for tool-using LLM agents.
Running

Agents

ResearchClawBench Task Submission

📦

Submit and validate a ResearchClawBench task ZIP

Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation

Paper • 2603.19220 • Published Mar 19 • 69
Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR

Paper • 2605.20164 • Published 30 days ago • 6
GoLongRL: Capability-Oriented Long Context Reinforcement Learning with Multitask Alignment

Paper • 2605.19577 • Published 30 days ago • 59
EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL

Paper • 2605.18703 • Published about 1 month ago • 50

High Quality Uncensored - GGUF on MLX

These are the empirically proven highest quality uncensored models on MLX.

dealignai/MiniMax-M2.7-JANGTQ-CRACK

Text Generation • 15B • Updated May 1 • 1.51k • 27
dealignai/Nemotron-3-Super-120B-A12B-UNCENSORED-JANG_2L

Text Generation • 13B • Updated Apr 25 • 2.81k • 11
dealignai/Gemma-4-26B-A4B-JANG_2L-CRACK

Image-Text-to-Text • 3B • Updated May 1 • 3.04k • 86
dealignai/Qwen3.5-VL-397B-A17B-UNCENSORED-JANG_1L

Image-Text-to-Text • 34B • Updated May 1 • 552 • 5

LTX-2.3 base models, quantized models and accompanying LoRAs and IC-LoRAs

Lightricks/LTX-2.3

Image-to-Video • Updated Apr 13 • 1.52M • 1.39k
Lightricks/LTX-2.3-fp8

Image-to-Video • Updated Mar 16 • 729k • 109
Lightricks/LTX-2.3-nvfp4

Image-to-Video • Updated Mar 17 • 11.5k • 86
Lightricks/LTX-2.3-22b-IC-LoRA-Motion-Track-Control

Any-to-Any • Updated Apr 13 • 55

CyberSec AI Portfolio - Datasets, Models & Spaces

80+ datasets, 35 Spaces & 4 models for cybersecurity AI: RGPD, NIS2, ISO 27001, DORA, AI Act, MITRE ATT&CK & more. By Ayi NEDJIMI.

AYI-NEDJIMI/CyberSec-Assistant-3B

Text Generation • Updated Feb 21 • 12 • 2
AYI-NEDJIMI/ISO27001-Expert-1.5B

Text Generation • Updated Feb 21 • 1 • 1
AYI-NEDJIMI/RGPD-Expert-1.5B

Text Generation • Updated Feb 21 • 2 • 1
AYI-NEDJIMI/m365-expert-v3

8B • Updated Feb 18 • 8 • 1

Streaming speech translation without the need for word-level alignments

Running

13

Hibiki Zero Samples

🏆

13

Demo samples of the speech translation model Hibiki-Zero.
Simultaneous Speech-to-Speech Translation Without Aligned Data

Paper • 2602.11072 • Published Feb 11 • 2
kyutai/Audio-NTREX-4L

Viewer • Updated Feb 12 • 3.6k • 744 • 5
kyutai/hibiki-zero-3b-pytorch-bf16

Audio-to-Audio • Updated Feb 12 • 2.09k • 56

WTF GENIUS PAPERS

Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models.

about 19 hours ago

Continuous Latent Diffusion Language Model

Paper • 2605.06548 • Published May 7 • 82
Scaling Latent Reasoning via Looped Language Models

Paper • 2510.25741 • Published Oct 29, 2025 • 231
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Paper • 2502.05171 • Published Feb 7, 2025 • 157
Pretraining Language Models to Ponder in Continuous Space

Paper • 2505.20674 • Published May 27, 2025 • 3

Previous
1
...
10
11
12
13
14
...
21,183
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs