Knut Jägersberg

KnutJaegersberg's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection 10 days ago

Laguna M.1

Collection

Our most capable model to date, designed for long-horizon work. Apache 2.0. • 4 items • Updated 8 days ago • 17

upvoted a collection 17 days ago

Gemma 4

Collection

Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 36 items • Updated 13 days ago • 222

upvoted a collection 18 days ago

Zamba2-VL

Collection

A suite of vision-language models based on Zamba2. • 3 items • Updated 20 days ago • 5

upvoted 2 collections 23 days ago

Gemma 4 QAT

Collection

Gemma 4 QAT (Quantization-Aware Training) for 3x less memory use and near original accuracy. • 16 items • Updated 13 days ago • 95

Gemma 4 QAT Q4_0

Collection

19 items • Updated 23 days ago • 139

upvoted a collection 27 days ago

Mellum 2

Collection

Mellum2 model weights • 6 items • Updated 27 days ago • 123

upvoted a collection 28 days ago

Cosmos3

Collection

Omnimodal World Models for Physical AI • 16 items • Updated 3 days ago • 132

upvoted 2 papers about 1 month ago

Self-Improving Language Models with Bidirectional Evolutionary Search

Paper • 2605.28814 • Published May 27 • 61

Triplet-Block Diffusion RWKV

Paper • 2605.25969 • Published May 25 • 25

upvoted 4 collections about 1 month ago

MiniCPM5

Collection

A SOTA 1B on-device LLM, small yet powerful. • 11 items • Updated May 26 • 27

Hy-MT2

Collection

混元翻译模型2.0版本 • 11 items • Updated May 26 • 44

Stable Audio 3

Collection

Stable Audio 3 Post-trained models • 3 items • Updated May 20 • 41

Intern-S2

Collection

2 items • Updated May 15 • 23

upvoted 3 collections about 2 months ago

Talkie 1930

Collection

Models based on Talkie 1930; conversions to hf transformers format and context extension to 32k. • 4 items • Updated 27 days ago • 2

jina-embeddings-v5-omni

Collection

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

Collection

8 items • Updated May 8 • 15

upvoted an article about 2 months ago

view article

Article

Granite 4.1 LLMs: How They’re Built

• 

ibm-granite

•

Apr 29

• 83

upvoted a collection about 2 months ago

Granite 4.1 Language Models

Collection

Efficient language models for multilingual generation, coding, RAG, and AI assistant workflows. • 6 items • Updated Apr 29 • 61

upvoted 2 collections 2 months ago

Embed Mamba2

Collection

Text embedding models based on Mamba2 with linear-time and constant-memory inference through vertical chunking. • 5 items • Updated Apr 21 • 3

Parcae

Collection

A family of stable looped models • 5 items • Updated Apr 24 • 6