Steffen Röcker's picture

Steffen Röcker PRO

sroecker

·

https://x.com/sroecker

AI & ML interests

Local models

Recent Activity

liked a model about 24 hours ago

nyrahealth/CrisperWhisper

liked a Space about 24 hours ago

hf-audio/open_asr_leaderboard

upvoted a collection 1 day ago

Organizations

sroecker's activity

upvoted a collection 1 day ago

OpenScholar_V1

The set of models, index, data associated with the paper "OpenScholar: Synthesizing Scientific Literature with Retrieval-Augmented LMs". • 7 items • Updated 3 days ago • 13

upvoted an article 2 days ago

Article

Low Code Large Language Model Alignment

By

•

2 days ago

• 12

upvoted a paper 4 days ago

Thinking LLMs: General Instruction Following with Thought Generation

Paper • 2410.10630 • Published Oct 14 • 16

upvoted an article 7 days ago

Article

ColFlor: Towards BERT-Size Vision-Language Document Retrieval Models

By

•

Oct 18

• 16

upvoted a collection 7 days ago

Athene-V2

2 items • Updated 7 days ago • 7

upvoted an article 8 days ago

Article

Releasing the largest multilingual open pretraining dataset

By

•

8 days ago

• 94

upvoted a collection 9 days ago

Marqo-Ecommerce-Embeddings

State-of-the-art embedding models fine-tuned for the ecommerce domain. +67% increase in evaluation metrics vs ViT-B-16-SigLIP. • 10 items • Updated 7 days ago • 16

upvoted a collection 10 days ago

Qwen2.5-Coder

Code-specific model series based on Qwen2.5 • 40 items • Updated 3 days ago • 223

upvoted a collection 11 days ago

kl3m

KL3M models and tokenizers • 7 items • Updated 11 days ago • 1

upvoted a collection 12 days ago

Moirai-R models

10 items • Updated 20 days ago • 33

upvoted an article 12 days ago

Article

SauerkrautLM's Multi-Phase Spectrum Training: A Technical Deep Dive

By

•

13 days ago

• 9

upvoted a collection 12 days ago

OpenCoder

OpenCoder is an open and reproducible code LLM family which matches the performance of top-tier code LLMs. • 9 items • Updated 4 days ago • 70

upvoted a paper 16 days ago

Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent

Paper • 2411.02265 • Published 17 days ago • 24

upvoted a collection 21 days ago

SmolLM2

State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 10 items • Updated about 4 hours ago • 172

upvoted an article 21 days ago

Article

Detoxifying the Commons

By

•

21 days ago

• 6

upvoted an article 23 days ago

Article

Decoding Strategies in Large Language Models

By

•

23 days ago

• 38

upvoted an article about 1 month ago

Article

Releasing Outlines-core 0.1.0: structured generation in Rust and Python

about 1 month ago

• 41

upvoted a collection about 1 month ago

LayerSkip

Models continually pretrained using LayerSkip - https://arxiv.org/abs/2404.16710 • 8 items • Updated about 4 hours ago • 43

upvoted an article about 1 month ago

Article

🇮🇹🇯🇵🇧🇷 Generating multilingual instruction datasets with Magpie 🐦‍⬛

By

•

Oct 21

• 18

upvoted a collection about 1 month ago

Flow-Judge-v0.1

Flow-Judge-v0.1 models • 5 items • Updated Sep 17 • 18