229 147 2774

Knut Jägersberg

KnutJaegersberg

jagersbergknut

AI & ML interests

NLP, opinion mining, narrative intelligence

Recent Activity

liked a model about 5 hours ago

silx-ai/Quasar-3.0-Final

liked a model about 23 hours ago

bartowski/open-thoughts_OpenThinker2-32B-GGUF

liked a dataset about 23 hours ago

open-thoughts/OpenThoughts2-1M

View all activity

Organizations

KnutJaegersberg's activity

liked a model about 5 hours ago

silx-ai/Quasar-3.0-Final

Text Generation • Updated 11 minutes ago • 5 • 1

liked a model about 23 hours ago

bartowski/open-thoughts_OpenThinker2-32B-GGUF

Text Generation • Updated 1 day ago • 466 • 7

liked a dataset about 23 hours ago

open-thoughts/OpenThoughts2-1M

Viewer • Updated 3 days ago • 1.04M • 1.22k • 39

liked a model 1 day ago

ibm-granite/granite-speech-3.2-8b

Automatic Speech Recognition • Updated 3 days ago • 296 • 33

upvoted a collection 1 day ago

Granite Speech

Collection

1 item • Updated 5 days ago • 5

liked a model 1 day ago

reducto/RolmOCR

Image-Text-to-Text • Updated 4 days ago • 366 • 116

upvoted a collection 2 days ago

Gemma 3 QAT

Collection

Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 8 items • Updated 3 days ago • 92

liked a model 2 days ago

google/gemma-3-27b-it-qat-q4_0-gguf

Image-Text-to-Text • Updated 3 days ago • 4.58k • 101

updated a model 5 days ago

KnutJaegersberg/GemmaCoder3-12B-Q8_0-GGUF

Updated 5 days ago • 5

published a model 5 days ago

KnutJaegersberg/GemmaCoder3-12B-Q8_0-GGUF

Updated 5 days ago • 5

liked a model 5 days ago

burtenshaw/GemmaCoder3-12B

Image-Text-to-Text • Updated 5 days ago • 267 • 35

updated a model 5 days ago

KnutJaegersberg/Qwen2.5-7B-Instruct-RLVR-Q8_0-GGUF

Updated 5 days ago • 6

published a model 5 days ago

KnutJaegersberg/Qwen2.5-7B-Instruct-RLVR-Q8_0-GGUF

Updated 5 days ago • 6

liked a model 5 days ago

virtuoussy/Qwen2.5-7B-Instruct-RLVR

Updated 4 days ago • 69 • 7

upvoted a collection 5 days ago

RLVR

Collection

Model and data for 'Expanding RL with Verifiable Rewards Across Diverse Domains' • 3 items • Updated 6 days ago • 10

liked a dataset 5 days ago

virtuoussy/Multi-subject-RLVR

Viewer • Updated 4 days ago • 579k • 438 • 42

reacted to BlinkDL's post with 🔥 8 days ago

Post

6041

RWKV-7 "Goose" 0.4B trained w/ ctx4k automatically extrapolates to ctx32k+, and perfectly solves NIAH ctx16k 🤯 100% RNN and attention-free. Only trained on the Pile. No finetuning. Replicable training runs. tested by our community: https://github.com/Jellyfish042/LongMamba

liked a model 8 days ago

vikhyatk/moondream2

Image-Text-to-Text • Updated 7 days ago • 177k • 1.1k

liked 2 models 11 days ago

Qwen/Qwen2.5-Omni-7B

Any-to-Any • Updated 6 days ago • 90k • 1.2k

Qwen/Qwen2.5-VL-32B-Instruct

Image-Text-to-Text • Updated 11 days ago • 240k • 317