Steffen Röcker's picture

Steffen Röcker PRO

sroecker

·

https://x.com/sroecker

AI & ML interests

Local models

Recent Activity

upvoted an article 1 day ago

Replicating DeepSeek R1 for Information Extraction

upvoted a collection 1 day ago

R1 Multilingual

upvoted a paper 1 day ago

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

View all activity

Organizations

sroecker's activity

upvoted an article 1 day ago

Article

Replicating DeepSeek R1 for Information Extraction

By

•

1 day ago

• 13

upvoted a collection 1 day ago

R1 Multilingual

5 items • Updated 1 day ago • 7

upvoted a paper 1 day ago

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

Paper • 2501.18511 • Published 2 days ago • 13

upvoted a collection 1 day ago

Tulu 3 Models

All models released with Tulu 3 -- state of the art open post-training recipes. • 10 items • Updated 3 days ago • 76

upvoted an article 5 days ago

Article

Open-R1: a fully open reproduction of DeepSeek-R1

5 days ago

• 534

upvoted a collection 6 days ago

Quantized DeepSeek R1 Distill

3 items • Updated 11 days ago • 3

upvoted a collection 8 days ago

DeepSeek-R1-abliterated

7 items • Updated 2 days ago • 16

upvoted a collection 9 days ago

Language Detection

StaticVectors models to detect language. Exports of FastText that run in NumPy without needing FastText • 2 items • Updated 6 days ago • 3

upvoted a collection 11 days ago

DeepSeek R1 AWQ

7 items • Updated 11 days ago • 4

upvoted a paper 13 days ago

CodeXEmbed: A Generalist Embedding Model Family for Multiligual and Multi-task Code Retrieval

Paper • 2411.12644 • Published Nov 19, 2024 • 3

upvoted a collection 18 days ago

InternLM3

6 items • Updated 16 days ago • 21

upvoted an article 19 days ago

Article

Python Is All You Need? Introducing Dria-Agent-α

By

•

22 days ago

• 22

upvoted a paper 23 days ago

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

Paper • 2501.01028 • Published about 1 month ago • 13

upvoted a collection 23 days ago

KaLM-embedding

7 items • Updated 10 days ago • 22

upvoted an article 24 days ago

Article

Synthetic Data Generation with FastData and Hugging Face

By

•

25 days ago

• 14

upvoted an article 26 days ago

Article

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

By

•

29 days ago

• 32

upvoted a collection 27 days ago

Dolphin 3.0

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 27 days ago • 60

upvoted an article 27 days ago

Article

Upgrading Kokoro: natural TTS for short bursts

By

•

Nov 22, 2024

• 26

upvoted an article about 1 month ago

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

•

about 1 month ago

• 39

upvoted a collection about 1 month ago

GLiNER

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