Cosmo's picture

Cosmo

cosmojg

·

https://cosmo.red

AI & ML interests

Machine learning and computational neuroscience

Recent Activity

liked a model 7 days ago

aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored

liked a model 7 days ago

SicariusSicariiStuff/Impish_Magic_24B

liked a model 7 days ago

SicariusSicariiStuff/Impish_Nemo_12B

View all activity

Organizations

None yet

upvoted 2 collections 29 days ago

Granite 4.0 Language Models

11 items • Updated 23 days ago • 159

Granite Quantized Models

Quantized versions of IBM Granite models. Licensed under the Apache 2.0 license. • 41 items • Updated 8 days ago • 21

upvoted 3 collections about 1 month ago

DeepSeek-V3.2

2 items • Updated Sep 29 • 441

Qwen3-Omni

6 items • Updated 22 days ago • 162

Granite Docling

5 items • Updated 23 days ago • 58

upvoted a collection about 2 months ago

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 30 days ago • 292

upvoted an article about 2 months ago

Article

🪆 Introduction to Matryoshka Embedding Models

Feb 23, 2024

• 178

upvoted a collection about 2 months ago

DeepSeek-V3.1

4 items • Updated Sep 22 • 243

upvoted a collection 3 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 • 245

upvoted a paper 4 months ago

Robust Learning of Diverse Code Edits

Paper • 2503.03656 • Published Mar 5 • 5

upvoted 4 collections 4 months ago

NextCoder

NextCoder family of code-editing LMs developed with Selective Knowledge Transfer and its training data. • 6 items • Updated Jul 9 • 71

T5Gemma

32 items • Updated Jul 10 • 73

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 • 337

Kimi-K2

Moonshot's MoE LLMs with 1 trillion parameters, exceptional on agentic intellegence • 3 items • Updated about 20 hours ago • 128

upvoted 2 articles 4 months ago

Article

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

Jul 9

• 698

Article

SmolLM3: smol, multilingual, long-context reasoner

Jul 8

• 705

upvoted a paper 4 months ago

Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs

Paper • 2505.04519 • Published May 7 • 5

upvoted a collection 4 months ago

Jamba 1.7

The AI21 Jamba family of models are hybrid SSM-Transformer foundation models, blending speed, efficient long context processing, and accuracy. • 4 items • Updated Jul 2 • 12

upvoted a paper 4 months ago

MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention

Paper • 2506.13585 • Published Jun 16 • 268

upvoted a collection 4 months ago

MiniMax-M1

MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model. • 6 items • Updated 10 days ago • 113