Knut Jägersberg

KnutJaegersberg

·

jagersbergknut

AI & ML interests

NLP, opinion mining, narrative intelligence

Recent Activity

liked a model 4 days ago

thinkingmachines/Inkling

liked a model 5 days ago

migtissera/Tess-4-9B-GGUF

liked a model 5 days ago

prism-ml/Bonsai-27B-gguf

View all activity

Organizations

upvoted a collection 5 days ago

Bonsai 27B

10 items • Updated 5 days ago • 174

upvoted 2 collections 11 days ago

LingBot-World-V2

2 items • Updated 11 days ago • 14

LingBot-Vision

5 items • Updated 13 days ago • 11

upvoted 5 collections about 1 month ago

Laguna M.1

Our most capable model to date, designed for long-horizon work. Apache 2.0. • 4 items • Updated 21 days ago • 20

Gemma 4

Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 43 items • Updated 1 day ago • 241

Zamba2-VL

A suite of vision-language models based on Zamba2. • 3 items • Updated Jun 9 • 5

Gemma 4 QAT

Gemma 4 QAT (Quantization-Aware Training) for 3x less memory use and near original accuracy. • 16 items • Updated 1 day ago • 107

Gemma 4 QAT Q4_0

19 items • Updated Jun 5 • 145

upvoted 2 collections about 2 months ago

Mellum 2

Mellum2 model weights • 6 items • Updated Jun 1 • 126

Cosmos3

Omnimodal World Models for Physical AI • 20 items • Updated 3 days ago • 152

upvoted 2 papers about 2 months ago

Self-Improving Language Models with Bidirectional Evolutionary Search

Paper • 2605.28814 • Published May 27 • 62

Triplet-Block Diffusion RWKV

Paper • 2605.25969 • Published May 25 • 25

upvoted 3 collections about 2 months ago

MiniCPM5

A SOTA 1B on-device LLM, small yet powerful. • 11 items • Updated May 26 • 39

Hy-MT2

混元翻译模型2.0版本 • 11 items • Updated May 26 • 45

Stable Audio 3

Stable Audio 3 Post-trained models • 3 items • Updated May 20 • 44

upvoted 4 collections 2 months ago

Intern-S2

4 items • Updated 3 days ago • 23

Talkie 1930

Models based on Talkie 1930; conversions to hf transformers format and context extension to 32k. • 4 items • Updated Jun 1 • 3

jina-embeddings-v5-omni

Multimodal (text + image + video + audio) embedding models aligned with jina-embeddings-v5-text-*. Two sizes, four task variants each. • 27 items • Updated May 12 • 36

EMO

8 items • Updated May 8 • 15

upvoted an article 3 months ago

Article

Granite 4.1 LLMs: How They’re Built

ibm-granite

•

Apr 29

• 84