12 173 624

Steffen Röcker PRO

sroecker

https://x.com/sroecker

AI & ML interests

Local models

Recent Activity

upvoted an article 4 days ago

DABStep: Data Agent Benchmark for Multi-step Reasoning

liked a model 4 days ago

allenai/Llama-3.1-Tulu-3.1-8B

liked a model 7 days ago

MultiLlasa/Llasa-1B-Multilingual-German

View all activity

Organizations

sroecker's activity

upvoted an article 4 days ago

Article

DABStep: Data Agent Benchmark for Multi-step Reasoning

13 days ago

• 47

liked a model 4 days ago

allenai/Llama-3.1-Tulu-3.1-8B

Text Generation • Updated 7 days ago • 210 • 19

liked a model 7 days ago

MultiLlasa/Llasa-1B-Multilingual-German

Updated 7 days ago • 76 • 7

upvoted a paper 8 days ago

On Teacher Hacking in Language Model Distillation

Paper • 2502.02671 • Published 13 days ago • 16

liked a dataset 9 days ago

opencompass/AIME2025

Viewer • Updated 9 days ago • 15 • 226 • 3

updated a collection 10 days ago

RLHF

Collection

2 items • Updated 10 days ago

liked a model 12 days ago

simplescaling/s1-32B

Text Generation • Updated 6 days ago • 8.47k • 273

liked a model 13 days ago

ibm-granite/granite-vision-3.1-2b-preview

Image-Text-to-Text • Updated about 8 hours ago • 5.17k • 61

upvoted a collection 13 days ago

EuroLLM

Collection

4 items • Updated Dec 2, 2024 • 28

upvoted a paper 13 days ago

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Paper • 2501.17161 • Published 20 days ago • 105

updated 2 models 13 days ago

sroecker/granite-3.1-2b-instruct-gptq

Text Generation • Updated 13 days ago • 23

sroecker/Qwen-1.B-GRPO-gsm8k-1000

Updated 13 days ago

published a model 13 days ago

sroecker/Qwen-1.B-GRPO-gsm8k-1000

Updated 13 days ago

updated a model 14 days ago

sroecker/granite-3.1-2b-instruct-4bit

Updated 14 days ago

published a model 14 days ago

sroecker/granite-3.1-2b-instruct-4bit

Updated 14 days ago

liked 2 datasets 14 days ago

TIGER-Lab/WebInstruct-CFT

Viewer • Updated 15 days ago • 654k • 698 • 41

ibm-research/nestful

Viewer • Updated 14 days ago • 1.86k • 1.01k • 13

liked a model 15 days ago

TurkuNLP/finerweb-quality-classifier

Updated about 1 month ago • 3.19k • 3

published a model 15 days ago

sroecker/granite-3.1-2b-instruct-gptq

Text Generation • Updated 13 days ago • 23

liked a model 15 days ago

bartowski/uncensoredai_UncensoredLM-DeepSeek-R1-Distill-Qwen-14B-GGUF

Text Generation • Updated 15 days ago • 52.5k • 18