Cosmo's picture

Cosmo

cosmojg

·

https://cosmo.red

AI & ML interests

Machine learning and computational neuroscience

Recent Activity

liked a model about 14 hours ago

janhq/Jan-v2-VL-high-gguf

liked a model about 14 hours ago

janhq/Jan-v2-VL-high

liked a model about 14 hours ago

janhq/Jan-v2-VL-med-gguf

View all activity

Organizations

None yet

upvoted a collection about 14 hours ago

Jan-v2-VL

Jan-v2-VL: an 8B VLM focused on reliable, many-step task execution. • 6 items • Updated 27 days ago • 37

upvoted 2 collections about 15 hours ago

Mistral Large 3

A state-of-the-art, open-weight, general-purpose multimodal model with a granular Mixture-of-Experts architecture. • 4 items • Updated 8 days ago • 73

Ministral 3

A collection of edge models, with Base, Instruct and Reasoning variants, in 3 different sizes: 3B, 8B and 14B. All with vision capabilities. • 9 items • Updated 8 days ago • 119

upvoted a collection 12 days ago

FLUX.2

Our second generation of FLUX • 2 items • Updated 15 days ago • 45

upvoted 3 collections 2 months ago

Granite 4.0 Language Models

13 items • Updated 23 days ago • 194

Granite Quantized Models

Quantized versions of IBM Granite models. Licensed under the Apache 2.0 license. • 44 items • Updated 19 days ago • 27

DeepSeek-V3.2

4 items • Updated 9 days ago • 507

upvoted 3 collections 3 months ago

Qwen3-Omni

6 items • Updated Oct 9 • 168

Granite Docling

5 items • Updated 23 days ago • 59

Apertus LLM

Democratizing Open and Compliant LLMs for Global Language Environments: 8B and 70B open-data open-weights models, multilingual in >1000 languages • 4 items • Updated Oct 1 • 307

upvoted an article 3 months ago

Article

🪆 Introduction to Matryoshka Embedding Models

Feb 23, 2024

•

181

upvoted a collection 3 months ago

DeepSeek-V3.1

4 items • Updated 13 days ago • 254

upvoted a collection 4 months ago

GLM-4.5

GLM-4.5: An open-source large language model designed for intelligent agents by Z.ai • 11 items • Updated Aug 11 • 249

upvoted a paper 5 months ago

Robust Learning of Diverse Code Edits

Paper • 2503.03656 • Published Mar 5 • 5

upvoted 4 collections 5 months ago

NextCoder

NextCoder family of code-editing LMs developed with Selective Knowledge Transfer and its training data. • 6 items • Updated Jul 9 • 72

T5Gemma

32 items • Updated Jul 10 • 77

MedGemma Release

Collection of Gemma 3 variants for performance on medical text and image comprehension to accelerate building healthcare-based AI applications. • 7 items • Updated Jul 11 • 357

Kimi-K2

Moonshot's MoE LLMs with 1 trillion parameters, exceptional on agentic intellegence • 5 items • Updated 26 days ago • 159

upvoted 2 articles 5 months ago

Article

Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders

Jul 9

•

723

Article

SmolLM3: smol, multilingual, long-context reasoner

+21

Jul 8

•

735