Steffen Röcker PRO

sroecker's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

liked a model about 10 hours ago

NovaSky-AI/Sky-T1-32B-Preview

Text Generation • Updated about 22 hours ago • 70 • 34

liked 2 models about 21 hours ago

EleutherAI/sae-llama-3.1-8b-64x

Updated Aug 31, 2024 • 10 • 12

Goodfire/Llama-3.1-8B-Instruct-SAE-l19

Updated about 12 hours ago • 2 • 14

liked 2 Spaces 2 days ago

Running on Zero

94

👀

Gaze Demo

Gaze detection using Moondream

Running

7

📊

DuckDB NSQL Leaderboard

upvoted a paper 2 days ago

KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model

Paper • 2501.01028 • Published 10 days ago • 10

upvoted a collection 2 days ago

KaLM-embedding

Collection

5 items • Updated 9 days ago • 18

liked a dataset 3 days ago

permutans/fineweb-bbc-news

Viewer • Updated about 8 hours ago • 4.44M • 66 • 7

upvoted an article 3 days ago

view article

Article

Synthetic Data Generation with FastData and Hugging Face

By •

4 days ago

• 12

upvoted an article 4 days ago

view article

Article

Fine-tune a SmolLM on domain-specific synthetic data from a LLM

By •

8 days ago

• 29

liked a model 5 days ago

MoritzLaurer/ModernBERT-large-zeroshot-v2.0

Text Classification • Updated 5 days ago • 1.16k • 23

liked a Space 6 days ago

Running

31

🥇

GIFT Eval

GIFT-Eval: A Benchmark for General Time Series Forecasting

upvoted a collection 6 days ago

Dolphin 3.0

Collection

Dolphin 3.0 is the next generation of the Dolphin series of instruct-tuned models. Designed to be the ultimate general purpose local model. • 7 items • Updated 6 days ago • 49

liked 2 models 6 days ago

cognitivecomputations/Dolphin3.0-Llama3.1-8B

Updated 6 days ago • 1.35k • 102

hexgrad/Kokoro-82M

Text-to-Speech • Updated 5 days ago • 8.1k • 646

upvoted an article 6 days ago

view article

Article

Upgrading Kokoro: natural TTS for short bursts

By •

Nov 22, 2024

• 17

upvoted an article 9 days ago

view article

Article

🐺🐦‍⬛ LLM Comparison/Test: DeepSeek-V3, QVQ-72B-Preview, Falcon3 10B, Llama 3.3 70B, Nemotron 70B in my updated MMLU-Pro CS benchmark

By •

9 days ago

• 36

upvoted a collection 9 days ago

GLiNER

Collection

Knowledgator GLiNER models for information extraction • 8 items • Updated Dec 9, 2024 • 9

liked 2 models 9 days ago

PowerInfer/SmallThinker-3B-Preview

Text Generation • Updated 5 days ago • 21.6k • 331

mrm8488/ModernBERT-base-ft-fineweb-edu-annotations

Text Classification • Updated 18 days ago • 404 • 11