Models
Datasets
Spaces
Docs
Enterprise
Pricing
Log In
Sign Up

Collections

Discover the best community collections!

Collections trending this week

Wan2.2-Lightx2v

lightx2v/Wan2.2-Distill-Models

Updated Dec 10, 2025 • 27.4k • 109
lightx2v/Wan2.2-Distill-Loras

Image-to-Video • Updated Dec 17, 2025 • 1.99M • • 205
lightx2v/Wan2.2-Official-Models

Updated Oct 28, 2025 • 9
lightx2v/Wan2.2-Lightning

Text-to-Video • Updated Nov 13, 2025 • 85 • 600

Ling-V2-abliterated

huihui-ai/Huihui-Ling-mini-2.0-abliterated

16B • Updated Oct 21, 2025 • 116 • 5
huihui-ai/Huihui-Ling-flash-2.0-abliterated-GGUF

103B • Updated Dec 6, 2025 • 36 • 5

Evo 2 is a genomic foundation model capable of generalist prediction and design tasks across DNA, RNA, and proteins.

arcinstitute/savanna_evo2_40b_base

Updated Sep 20, 2025 • 4 • 2
arcinstitute/savanna_evo2_40b

Updated Sep 20, 2025 • 7 • 10
arcinstitute/evo2_40b_base

Updated Sep 20, 2025 • 114 • 11
arcinstitute/savanna_evo2_1b_base

Updated Sep 20, 2025 • 22

granite-4.0-abliterated

huihui-ai/Huihui-granite-4.0-micro-abliterated

Text Generation • 3B • Updated Oct 3, 2025 • 104 • 4
huihui-ai/Huihui-granite-4.0-h-micro-abliterated

Text Generation • 3B • Updated Oct 3, 2025 • 15 • 5
huihui-ai/Huihui-granite-4.0-h-tiny-abliterated

Text Generation • 7B • Updated Oct 4, 2025 • 9 • 9

LLM Step-Provers in Lean4

ByteDance-Seed/BFS-Prover-V2-32B

Text Generation • 33B • Updated Oct 9, 2025 • 63 • 12
ByteDance-Seed/BFS-Prover-V1-7B

Text Generation • 8B • Updated Oct 14, 2025 • 78 • • 25
ByteDance-Seed/BFS-Prover-V2-7B

Text Generation • 8B • Updated Oct 9, 2025 • 83 • 6
BFS-Prover: Scalable Best-First Tree Search for LLM-based Automatic Theorem Proving

Paper • 2502.03438 • Published Feb 5, 2025 • 2

Sparse Auto-Encoders (SAEs) for Mechanistic Interpretability

A compilation of sparse auto-encoders trained on large language models.

EleutherAI/sae-DeepSeek-R1-Distill-Qwen-1.5B-65k

Updated Jan 26, 2025 • 4 • 7
EleutherAI/skip-transcoder-DeepSeek-R1-Distill-Qwen-1.5B-65k

Updated Jan 26, 2025 • 3 • 4
EleutherAI/sae-pythia-70m-32k

Updated Aug 5, 2024
EleutherAI/sae-pythia-160m-32k

Updated Aug 5, 2024 • 1

Qwen3-Omni-abliterated

huihui-ai/Huihui-Qwen3-Omni-30B-A3B-Instruct-abliterated

35B • Updated Oct 7, 2025 • 557 • 13
huihui-ai/Huihui-Qwen3-Omni-30B-A3B-Captioner-abliterated

32B • Updated Oct 10, 2025 • 66 • 3
huihui-ai/Huihui-Qwen3-Omni-30B-A3B-Thinking-abliterated

32B • Updated Oct 19, 2025 • 564 • 4

Hubble Datasets

Perturbation datasets used to train the Hubble models, covering three risk domains and five data types.

allegrolab/testset_popqa

Viewer • Updated Jun 13, 2025 • 8k • 106
allegrolab/testset_winogrande-infill

Viewer • Updated Jun 13, 2025 • 8k • 102
allegrolab/testset_winogrande-mcq

Viewer • Updated Jun 13, 2025 • 8k • 91
allegrolab/testset_mmlu

Viewer • Updated Jun 13, 2025 • 8k • 116

Ming is the multi-modal series of any-to-any models developed by Ant Ling team.

inclusionAI/Ming-flash-omni-2.0

Any-to-Any • Updated 19 days ago • 9.27k • 252
inclusionAI/Ming-omni-tts-16.8B-A3B

Text-to-Speech • 18B • Updated 6 days ago • 112 • 26
inclusionAI/Ming-omni-tts-0.5B

Text-to-Speech • 2B • Updated 6 days ago • 3.48k • 31
inclusionAI/Ming-omni-tts-tokenizer-12Hz

Audio-to-Audio • 0.8B • Updated 6 days ago • 66 • 5

Eight models that vary in size, data condition, and corpus scale to establish dilution effects in memorization.

allegrolab/hubble-8b-500b_toks-perturbed-hf

Text Generation • 8B • Updated Oct 23, 2025 • 172 • 1
allegrolab/hubble-8b-500b_toks-standard-hf

Text Generation • 8B • Updated Oct 23, 2025 • 50 • 1
allegrolab/hubble-8b-100b_toks-perturbed-hf

Text Generation • 8B • Updated Oct 23, 2025 • 77
allegrolab/hubble-8b-100b_toks-standard-hf

Text Generation • 8B • Updated Oct 23, 2025 • 27

Wan2.2-Lightx2v

lightx2v/Wan2.2-Distill-Models

Updated Dec 10, 2025 • 27.4k • 109
lightx2v/Wan2.2-Distill-Loras

Image-to-Video • Updated Dec 17, 2025 • 1.99M • • 205
lightx2v/Wan2.2-Official-Models

Updated Oct 28, 2025 • 9
lightx2v/Wan2.2-Lightning

Text-to-Video • Updated Nov 13, 2025 • 85 • 600

Sparse Auto-Encoders (SAEs) for Mechanistic Interpretability

A compilation of sparse auto-encoders trained on large language models.

EleutherAI/sae-DeepSeek-R1-Distill-Qwen-1.5B-65k

Updated Jan 26, 2025 • 4 • 7
EleutherAI/skip-transcoder-DeepSeek-R1-Distill-Qwen-1.5B-65k

Updated Jan 26, 2025 • 3 • 4
EleutherAI/sae-pythia-70m-32k

Updated Aug 5, 2024
EleutherAI/sae-pythia-160m-32k

Updated Aug 5, 2024 • 1

Ling-V2-abliterated

huihui-ai/Huihui-Ling-mini-2.0-abliterated

16B • Updated Oct 21, 2025 • 116 • 5
huihui-ai/Huihui-Ling-flash-2.0-abliterated-GGUF

103B • Updated Dec 6, 2025 • 36 • 5

Qwen3-Omni-abliterated

huihui-ai/Huihui-Qwen3-Omni-30B-A3B-Instruct-abliterated

35B • Updated Oct 7, 2025 • 557 • 13
huihui-ai/Huihui-Qwen3-Omni-30B-A3B-Captioner-abliterated

32B • Updated Oct 10, 2025 • 66 • 3
huihui-ai/Huihui-Qwen3-Omni-30B-A3B-Thinking-abliterated

32B • Updated Oct 19, 2025 • 564 • 4

Evo 2 is a genomic foundation model capable of generalist prediction and design tasks across DNA, RNA, and proteins.

arcinstitute/savanna_evo2_40b_base

Updated Sep 20, 2025 • 4 • 2
arcinstitute/savanna_evo2_40b

Updated Sep 20, 2025 • 7 • 10
arcinstitute/evo2_40b_base

Updated Sep 20, 2025 • 114 • 11
arcinstitute/savanna_evo2_1b_base

Updated Sep 20, 2025 • 22

Hubble Datasets

Perturbation datasets used to train the Hubble models, covering three risk domains and five data types.

allegrolab/testset_popqa

Viewer • Updated Jun 13, 2025 • 8k • 106
allegrolab/testset_winogrande-infill

Viewer • Updated Jun 13, 2025 • 8k • 102
allegrolab/testset_winogrande-mcq

Viewer • Updated Jun 13, 2025 • 8k • 91
allegrolab/testset_mmlu

Viewer • Updated Jun 13, 2025 • 8k • 116

granite-4.0-abliterated

huihui-ai/Huihui-granite-4.0-micro-abliterated

Text Generation • 3B • Updated Oct 3, 2025 • 104 • 4
huihui-ai/Huihui-granite-4.0-h-micro-abliterated

Text Generation • 3B • Updated Oct 3, 2025 • 15 • 5
huihui-ai/Huihui-granite-4.0-h-tiny-abliterated

Text Generation • 7B • Updated Oct 4, 2025 • 9 • 9

Ming is the multi-modal series of any-to-any models developed by Ant Ling team.

inclusionAI/Ming-flash-omni-2.0

Any-to-Any • Updated 19 days ago • 9.27k • 252
inclusionAI/Ming-omni-tts-16.8B-A3B

Text-to-Speech • 18B • Updated 6 days ago • 112 • 26
inclusionAI/Ming-omni-tts-0.5B

Text-to-Speech • 2B • Updated 6 days ago • 3.48k • 31
inclusionAI/Ming-omni-tts-tokenizer-12Hz

Audio-to-Audio • 0.8B • Updated 6 days ago • 66 • 5

LLM Step-Provers in Lean4

ByteDance-Seed/BFS-Prover-V2-32B

Text Generation • 33B • Updated Oct 9, 2025 • 63 • 12
ByteDance-Seed/BFS-Prover-V1-7B

Text Generation • 8B • Updated Oct 14, 2025 • 78 • • 25
ByteDance-Seed/BFS-Prover-V2-7B

Text Generation • 8B • Updated Oct 9, 2025 • 83 • 6
BFS-Prover: Scalable Best-First Tree Search for LLM-based Automatic Theorem Proving

Paper • 2502.03438 • Published Feb 5, 2025 • 2

Eight models that vary in size, data condition, and corpus scale to establish dilution effects in memorization.

allegrolab/hubble-8b-500b_toks-perturbed-hf

Text Generation • 8B • Updated Oct 23, 2025 • 172 • 1
allegrolab/hubble-8b-500b_toks-standard-hf

Text Generation • 8B • Updated Oct 23, 2025 • 50 • 1
allegrolab/hubble-8b-100b_toks-perturbed-hf

Text Generation • 8B • Updated Oct 23, 2025 • 77
allegrolab/hubble-8b-100b_toks-standard-hf

Text Generation • 8B • Updated Oct 23, 2025 • 27

Previous
1
...
34
35
36
37
38
...
18,683
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs