Knut Jägersberg's picture

Knut Jägersberg

KnutJaegersberg

·

jagersbergknut

AI & ML interests

NLP, opinion mining, narrative intelligence

Articles

Perspectives for first principles prompt engineering

Towards actively reasoning LLM systems

Organizations

KnutJaegersberg's activity

upvoted a collection 8 days ago

SmolLM2

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 8 items • Updated 5 days ago • 160

upvoted a collection 10 days ago

QTIP Quantized Models

See https://github.com/Cornell-RelaxML/qtip • 27 items • Updated 13 days ago • 5

upvoted a paper 12 days ago

GPT-4o System Card

Paper • 2410.21276 • Published 15 days ago • 76

upvoted an article 13 days ago

Article

Visually Multilingual: Introducing mcdse-2b

By

•

13 days ago

• 37

upvoted 2 collections 14 days ago

October 25 Releases

19 items • Updated 15 days ago • 7

LongVU

7 items • Updated 9 days ago • 26

upvoted a collection 17 days ago

VILA-U-7B

VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation • 2 items • Updated 19 days ago • 4

upvoted a collection 19 days ago

CompassJudger

4 items • Updated 25 days ago • 7

upvoted a paper 22 days ago

SpiRit-LM: Interleaved Spoken and Written Language Model

Paper • 2402.05755 • Published Feb 8 • 12

upvoted a collection 23 days ago

VPTQ Mistral Large Instruct 2407 without finetune

arxiv.org/abs/2409.17066, VPTQ Mistral Large Instruct 2407 without finetune • 8 items • Updated 23 days ago • 1

upvoted a paper 23 days ago

Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models

Paper • 2410.02416 • Published Oct 3 • 25

upvoted a collection 25 days ago

Gemma-APS Release

Gemma models for text-to-propositions segmentation. The models are distilled from fine-tuned Gemini Pro model applied to multi-domain synthetic data. • 3 items • Updated 25 days ago • 19

upvoted a paper 25 days ago

Scalable and Domain-General Abstractive Proposition Segmentation

Paper • 2406.19803 • Published Jun 28 • 2

upvoted an article 29 days ago

Article

MicroJAX

By

•

Aug 25

• 15

upvoted a paper about 1 month ago

Falcon Mamba: The First Competitive Attention-free 7B Language Model

Paper • 2410.05355 • Published Oct 7 • 27

upvoted 2 collections about 1 month ago

ProLong

ProLong is a family of long-context models that are continued trained and supervised fine-tuned from Llama-3-8B, with a maximum context window of 512K • 7 items • Updated 18 days ago • 4

Salamandra 🦎

13 items • Updated 2 days ago • 36

upvoted an article about 1 month ago

Article

Uncensor any LLM with abliteration

By

•

Jun 13

• 362

upvoted a collection about 1 month ago

Molmo

Artifacts for open multimodal language models. • 5 items • Updated Sep 26 • 269

upvoted a collection about 2 months ago

Llama 3.2

This collection hosts the transformers and original repos of the Llama 3.2 and Llama Guard 3 • 15 items • Updated 16 days ago • 451