sroecker (Steffen Röcker)

upvoted a collection 3 days ago

xLAM models

Collection

6 items • Updated 4 days ago • 19

upvoted 2 collections 4 days ago

Mistral NeMo

Collection

6 items • Updated 4 days ago • 5

em🍞ing series

Collection

crispy sentence embedding family • 4 items • Updated 4 days ago • 19

upvoted 2 articles 4 days ago

Article

Introduction to Quantization cooked in 🤗 with 💗🧑‍🍳

By

•

Aug 25, 2023

• 8

Article

Docmatix - a huge dataset for Document Visual Question Answering

5 days ago

• 43

upvoted 2 articles 5 days ago

Article

Announcing BigCodeBench-Hard, and More

By

•

5 days ago

• 6

Article

How we leveraged distilabel to create an Argilla 2.0 Chatbot

7 days ago

• 28

upvoted an article 6 days ago

Article

SmolLM - blazingly fast and remarkably powerful

7 days ago

• 152

upvoted a paper 6 days ago

Qwen2 Technical Report

Paper • 2407.10671 • Published 7 days ago • 142

upvoted an article 7 days ago

Article

The Rise of Agentic Data Generation

By

•

7 days ago

• 66

upvoted an article 11 days ago

Article

How to run Gemini Nano locally in your browser

By

•

11 days ago

• 36

upvoted a paper 11 days ago

AgentInstruct: Toward Generative Teaching with Agentic Flows

Paper • 2407.03502 • Published 19 days ago • 34

upvoted an article 12 days ago

Article

Experimenting with Automatic PII Detection on the Hub using Presidio

13 days ago

• 19

upvoted a paper 12 days ago

ChartGemma: Visual Instruction-tuning for Chart Reasoning in the Wild

Paper • 2407.04172 • Published 18 days ago • 19

upvoted an article 13 days ago

Article

The Great LLM Showdown: Amy's Quest for the Perfect LLM

By

•

13 days ago

• 11

upvoted a collection 20 days ago

🇩🇪German SFT and DPO datasets

Collection

Datasets that can be used for LLM training with axolotl, trl or llama_factory. • 30 items • Updated May 27 • 9

upvoted an article 24 days ago

Article

Welcome Gemma 2 - Google's new open LLM

26 days ago

• 97

upvoted a collection 25 days ago

Gemma 2 Release

Collection

10 items • Updated 25 days ago • 129

upvoted a paper 26 days ago

The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale

Paper • 2406.17557 • Published 27 days ago • 75

upvoted 2 articles 28 days ago

Article

Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models

29 days ago

• 142

Article

BM25 for Python: Achieving high performance while simplifying dependencies with BM25S⚡

By

•

13 days ago

• 29

upvoted a paper 29 days ago

GenQA: Generating Millions of Instructions from a Handful of Prompts

Paper • 2406.10323 • Published Jun 14 • 5

upvoted a collection 29 days ago

Embedding Model Datasets

Collection

A curated subset of the datasets that work out of the box with Sentence Transformers: https://huggingface.co/datasets?other=sentence-transformers • 67 items • Updated 19 days ago • 52

upvoted a collection 30 days ago

4M Models

Collection

Multimodal models from https://4m.epfl.ch/ • 14 items • Updated Jun 14 • 29

upvoted 2 papers about 1 month ago

GLiNER multi-task: Generalist Lightweight Model for Various Information Extraction Tasks

Paper • 2406.12925 • Published Jun 14 • 20

Instruction Pre-Training: Language Models are Supervised Multitask Learners

Paper • 2406.14491 • Published Jun 20 • 76

upvoted 2 collections about 1 month ago

Instruction Pre-Training

Collection

8 items • Updated Jun 21 • 24

Hermes

Collection

Nous' Flagship LLM Series • 23 items • Updated 25 days ago • 98

upvoted a paper about 1 month ago

Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models

Paper • 2404.18796 • Published Apr 29 • 67

upvoted 7 collections about 1 month ago

upvoted a paper about 1 month ago

Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing

Paper • 2406.08464 • Published Jun 12 • 49

upvoted an article about 1 month ago

Article

Putting RL back in RLHF

Jun 12

• 55

upvoted a collection about 1 month ago

codestral-text2cypher

Collection

codestral finetuned for text2cypher • 3 items • Updated Jun 10 • 2

upvoted 4 collections about 2 months ago

Local Function Calling Gems

Collection

These are the best function calling LLMs one can run on less than 64GB VRAM/Unified Memory. I use these on a M1 Max Macbook 64GB. • 6 items • Updated 21 days ago • 3

Qwen2

Collection

Qwen2 language models, including pretrained and instruction-tuned models of 5 sizes, including 0.5B, 1.5B, 7B, 57B-A14B, and 72B. • 29 items • Updated Jun 6 • 260

GLM-4

Collection

GLM-4 Open Models • 4 items • Updated Jun 5 • 88

DeTikZify

Collection

Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ • 9 items • Updated Jun 3 • 2

upvoted 4 articles about 2 months ago

Article

Uncensor any LLM with abliteration

By

•

Jun 13

• 238

Article

Releasing Common Corpus: the largest public domain dataset for training LLMs

By

•

Mar 20

• 13

Article

How to directly access 150k+ Hugging Face Datasets with DuckDB and query using GPT-4o

By

•

May 31

• 10

Article

⚗️ 🔥 Building High-Quality Datasets with distilabel and Prometheus 2

By

•

Jun 3

• 21

upvoted a collection about 2 months ago

sentence-transformers-from-synthetic-data

Collection

Example of using distilabel to generate synthetic triplets data for fine-tuning a Sentence Transformer model • 4 items • Updated Jun 21 • 20

upvoted an article about 2 months ago

Article

Training and Finetuning Embedding Models with Sentence Transformers v3

May 28

• 124

upvoted a paper about 2 months ago

Granite Code Models: A Family of Open Foundation Models for Code Intelligence

Paper • 2405.04324 • Published May 7 • 15

upvoted a collection about 2 months ago

🤖Phi-3

Collection

6 items • Updated 1 day ago • 2

upvoted an article about 2 months ago

Article

GPU Poor Savior: Revolutionizing Low-Bit Open Source LLMs and Cost-Effective Edge Computing

By

•

May 25

• 9

upvoted 3 collections about 2 months ago

DiscoLeo 8B: Llama3 for German

Collection

Continued Pretraining on Llama3 8B to improve German linguistic capabilities. A collection of base and fine-tuned models and variants. • 5 items • Updated May 25 • 14

DiscoLeo 8B quants

Collection

A collection of different quantizations of the DiscoLeo models. • 3 items • Updated May 25 • 3

C4AI Aya 23

Collection

Aya 23 is an open weights research release of an instruction fine-tuned model with highly advanced multilingual capabilities. • 3 items • Updated May 23 • 40

upvoted an article about 2 months ago

Article

⚗️ 🧑🏼‍🌾 Let's grow some Domain Specific Datasets together

By

•

Apr 29

• 28

upvoted a collection about 2 months ago

C4AI Command R Plus

Collection

C4AI Command R+ is an open weights research release of a 104B billion parameter model with highly advanced capabilities. • 3 items • Updated May 23 • 27

upvoted an article 2 months ago

Article

Let's talk about LLM evaluation

By

•

May 23

• 95

upvoted 2 collections 2 months ago

Phi-3

Collection

Phi-3 family of small language and multi-modal models. Language models are available in short- and long-context lengths. • 23 items • Updated 11 days ago • 372

CommonCatalog

Collection

Common Catalog, a dataset with Creative Commons licensed images and machine-generated caption pairs • 8 items • Updated May 16 • 13

Steffen Röcker PRO

AI & ML interests

Organizations

sroecker's activity

Introduction to Quantization cooked in 🤗 with 💗🧑‍🍳

Docmatix - a huge dataset for Document Visual Question Answering

Announcing BigCodeBench-Hard, and More

How we leveraged distilabel to create an Argilla 2.0 Chatbot

SmolLM - blazingly fast and remarkably powerful

The Rise of Agentic Data Generation

How to run Gemini Nano locally in your browser

Experimenting with Automatic PII Detection on the Hub using Presidio

The Great LLM Showdown: Amy's Quest for the Perfect LLM

Welcome Gemma 2 - Google's new open LLM

Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models

BM25 for Python: Achieving high performance while simplifying dependencies with *BM25S*⚡

Putting RL back in RLHF

Uncensor any LLM with abliteration

Releasing Common Corpus: the largest public domain dataset for training LLMs

How to directly access 150k+ Hugging Face Datasets with DuckDB and query using GPT-4o

⚗️ 🔥 Building High-Quality Datasets with distilabel and Prometheus 2

Training and Finetuning Embedding Models with Sentence Transformers v3

GPU Poor Savior: Revolutionizing Low-Bit Open Source LLMs and Cost-Effective Edge Computing

⚗️ 🧑🏼‍🌾 Let's grow some Domain Specific Datasets together

Let's talk about LLM evaluation

BM25 for Python: Achieving high performance while simplifying dependencies with BM25S⚡