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

Sentence Transformers

Sentence Transformers are BERT-based models that map sentences and paragraphs to dense vector embeddings for semantic similarity, search, etc..

keras/all_minilm_l12_v2_en

Updated 24 days ago • 27
keras/all_minilm_l6_v1_en

Updated 24 days ago • 32
keras/all_minilm_l6_v2_en

Updated 24 days ago • 29
keras/paraphrase_minilm_l3_v2_en

Updated 24 days ago • 31

RedHatAI/gemma-4-31B-it-FP8-block

Image-Text-to-Text • 31B • Updated about 21 hours ago • 4.13M • 44

Esper 4 is an agentic finetune focused on code, DevOps, architecture, and MLOps! Currently available for Qwen 3.6 and Gemma 4.

ValiantLabs/Qwen3.6-27B-Esper4

Image-Text-to-Text • 28B • Updated 24 days ago • 292 • 19
ValiantLabs/gemma-4-12B-it-Esper4

Image-Text-to-Text • 12B • Updated 24 days ago • 422 • 10

Next-generation Mixture-of-Experts (MoE) model optimized for advanced agentic coding and complex reasoning.

keras/qwen3_6_moe_35b_a3b

Text Generation • Updated 24 days ago • 439

prism-ml/Ternary-Bonsai-27B-gguf

Text Generation • 27B • Updated 21 days ago • 796k • • 1.18k

FLUX.1-Krea-dev

Runtime error

MCP

25

FLUX.1 Krea Dev

📚

25

Krea Dev - generate natural, lifelike professional images

Multilingual E5

State-of-the-art multilingual text embeddings for semantic search and dense retrieval.

keras/multilingual_e5_small

Updated 24 days ago • 35
keras/multilingual_e5_base

Updated 24 days ago • 34
keras/multilingual_e5_large

Updated 24 days ago • 33

CausalGame Reproduction (ICML 2026 #16331)

Artifacts for reproducing CausalGame: 14-setting causal-thinking benchmark for LLM agents. Bundle, results, oracle baselines.

Running

Repro - CausalGame: Benchmarking Causal Thinking of LLM Agents in Games

🎯

Explore game causal benchmarks with an interactive logbook
arinpt/causalgame-repro

Updated 24 days ago • 305
arinpt/causalgame-jobs

1.77 MB
arinpt/Repro-CausalGame-Benchmarking-Causal-Thinking-of-LLM-Agents-artifacts

2.1 MB

Highly efficient Mixture-of-Experts (MoE) large language model for advanced reasoning and text generation.

keras/qwen3_5_moe_35b_a3b_base

Text Generation • Updated about 14 hours ago • 434
keras/qwen3_5_moe_35b_a3b

Text Generation • Updated about 14 hours ago • 437

Harrier Embedding

Microsoft's harrier is a decoder-only, multilingual text embedding model family using last-token pooling and L2 normalization to generate Embeddings

keras/harrier_embedding_oss_270m

Updated 24 days ago • 32
keras/harrier_embedding_oss_0.6b

Updated 24 days ago • 22

Sentence Transformers

Sentence Transformers are BERT-based models that map sentences and paragraphs to dense vector embeddings for semantic similarity, search, etc..

keras/all_minilm_l12_v2_en

Updated 24 days ago • 27
keras/all_minilm_l6_v1_en

Updated 24 days ago • 32
keras/all_minilm_l6_v2_en

Updated 24 days ago • 29
keras/paraphrase_minilm_l3_v2_en

Updated 24 days ago • 31

FLUX.1-Krea-dev

Runtime error

MCP

25

FLUX.1 Krea Dev

📚

25

Krea Dev - generate natural, lifelike professional images

RedHatAI/gemma-4-31B-it-FP8-block

Image-Text-to-Text • 31B • Updated about 21 hours ago • 4.13M • 44

Multilingual E5

State-of-the-art multilingual text embeddings for semantic search and dense retrieval.

keras/multilingual_e5_small

Updated 24 days ago • 35
keras/multilingual_e5_base

Updated 24 days ago • 34
keras/multilingual_e5_large

Updated 24 days ago • 33

Esper 4 is an agentic finetune focused on code, DevOps, architecture, and MLOps! Currently available for Qwen 3.6 and Gemma 4.

ValiantLabs/Qwen3.6-27B-Esper4

Image-Text-to-Text • 28B • Updated 24 days ago • 292 • 19
ValiantLabs/gemma-4-12B-it-Esper4

Image-Text-to-Text • 12B • Updated 24 days ago • 422 • 10

CausalGame Reproduction (ICML 2026 #16331)

Artifacts for reproducing CausalGame: 14-setting causal-thinking benchmark for LLM agents. Bundle, results, oracle baselines.

Running

Repro - CausalGame: Benchmarking Causal Thinking of LLM Agents in Games

🎯

Explore game causal benchmarks with an interactive logbook
arinpt/causalgame-repro

Updated 24 days ago • 305
arinpt/causalgame-jobs

1.77 MB
arinpt/Repro-CausalGame-Benchmarking-Causal-Thinking-of-LLM-Agents-artifacts

2.1 MB

Next-generation Mixture-of-Experts (MoE) model optimized for advanced agentic coding and complex reasoning.

keras/qwen3_6_moe_35b_a3b

Text Generation • Updated 24 days ago • 439

Highly efficient Mixture-of-Experts (MoE) large language model for advanced reasoning and text generation.

keras/qwen3_5_moe_35b_a3b_base

Text Generation • Updated about 14 hours ago • 434
keras/qwen3_5_moe_35b_a3b

Text Generation • Updated about 14 hours ago • 437

prism-ml/Ternary-Bonsai-27B-gguf

Text Generation • 27B • Updated 21 days ago • 796k • • 1.18k

Harrier Embedding

Microsoft's harrier is a decoder-only, multilingual text embedding model family using last-token pooling and L2 normalization to generate Embeddings

keras/harrier_embedding_oss_270m

Updated 24 days ago • 32
keras/harrier_embedding_oss_0.6b

Updated 24 days ago • 22

Previous
1
...
621
622
623
624
625
...
22,341
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs