Steffen Röcker's picture

Steffen Röcker PRO

sroecker

·

https://x.com/sroecker

AI & ML interests

Local models

Recent Activity

liked a dataset about 1 hour ago

cognitivecomputations/dolphin-r1

liked a model about 1 hour ago

qresearch/DeepSeek-R1-Distill-Llama-70B-SAE-l48

liked a dataset 1 day ago

open-thoughts/OpenThoughts-114k

View all activity

Organizations

sroecker's activity

upvoted an article 2 days ago

Article

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

2 days ago

• 414

upvoted a collection 3 days ago

Quantized DeepSeek R1 Distill

3 items • Updated 8 days ago • 3

upvoted a collection 5 days ago

DeepSeek-R1-abliterated

6 items • Updated about 6 hours ago • 10

upvoted a collection 6 days ago

Language Detection

StaticVectors models to detect language. Exports of FastText that run in NumPy without needing FastText • 2 items • Updated 4 days ago • 3

upvoted a collection 8 days ago

DeepSeek R1 AWQ

7 items • Updated 8 days ago • 4

upvoted a paper 11 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 15 days ago

InternLM3

6 items • Updated 13 days ago • 21

upvoted an article 16 days ago

Article

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

By

•

19 days ago

• 22

upvoted a paper 21 days ago

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

Paper • 2501.01028 • Published 28 days ago • 13

upvoted a collection 21 days ago

KaLM-embedding

7 items • Updated 7 days ago • 22

upvoted an article 22 days ago

Article

Synthetic Data Generation with FastData and Hugging Face

By

•

23 days ago

• 14

upvoted an article 23 days ago

Article

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

By

•

27 days ago

• 32

upvoted a collection 25 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 25 days ago • 60

upvoted an article 25 days ago

Article

Upgrading Kokoro: natural TTS for short bursts

By

•

Nov 22, 2024

• 26

upvoted an article 27 days 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

•

28 days ago

• 39

upvoted a collection 27 days ago

GLiNER

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

upvoted an article 29 days ago

Article

Fine-tune ModernBERT for text classification using synthetic data

By

•

about 1 month ago

• 28

upvoted a collection about 1 month ago

4chan data (public)

1 item • Updated about 1 month ago • 1

upvoted a paper about 1 month ago

YuLan-Mini: An Open Data-efficient Language Model

Paper • 2412.17743 • Published Dec 23, 2024 • 64

upvoted a collection about 1 month ago

YuLan-Mini

A highly capable 2.4B lightweight LLM using only 1T pre-training data with all details. • 5 items • Updated Dec 29, 2024 • 12