12 171 621

Steffen Röcker PRO

sroecker

https://x.com/sroecker

AI & ML interests

Local models

Recent Activity

liked a model 1 day ago

simplescaling/s1-32B

liked a model 2 days ago

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

upvoted a collection 2 days ago

EuroLLM

View all activity

Organizations

sroecker's activity

liked a model 1 day ago

simplescaling/s1-32B

Text Generation • Updated 3 days ago • 1.34k • 114

liked a model 2 days ago

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

Image-Text-to-Text • Updated 2 days ago • 876 • 12

upvoted a collection 2 days ago

EuroLLM

Collection

4 items • Updated Dec 2, 2024 • 27

upvoted a paper 2 days ago

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

Paper • 2501.17161 • Published 9 days ago • 100

updated 2 models 2 days ago

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

Text Generation • Updated 2 days ago • 17

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

Updated 2 days ago

published a model 2 days ago

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

Updated 2 days ago

updated a model 3 days ago

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

Updated 3 days ago

published a model 3 days ago

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

Updated 3 days ago

liked 2 datasets 3 days ago

TIGER-Lab/WebInstruct-CFT

Viewer • Updated 5 days ago • 654k • 217 • 36

ibm-research/nestful

Viewer • Updated 4 days ago • 1.86k • 613 • 12

liked a model 4 days ago

TurkuNLP/finerweb-quality-classifier

Updated 20 days ago • 90 • 3

published a model 4 days ago

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

Text Generation • Updated 2 days ago • 17

liked 2 models 4 days ago

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

Text Generation • Updated 5 days ago • 19.6k • 9

uncensoredai/UncensoredLM-DeepSeek-R1-Distill-Qwen-14B

Updated 5 days ago • 202 • 8

upvoted an article 6 days ago

Article

Replicating DeepSeek R1 for Information Extraction

•

6 days ago

• 28

upvoted a collection 6 days ago

R1 Multilingual

Collection

5 items • Updated 6 days ago • 7

upvoted a paper 6 days ago

WILDCHAT-50M: A Deep Dive Into the Role of Synthetic Data in Post-Training

Paper • 2501.18511 • Published 7 days ago • 17

liked a model 6 days ago

allenai/Llama-3.1-Tulu-3-8B

Text Generation • Updated 8 days ago • 13.2k • 141

upvoted a collection 6 days ago

Tulu 3 Models

Collection

All models released with Tulu 3 -- state of the art open post-training recipes. • 10 items • Updated 8 days ago • 86