S. Smits's picture

S. Smits

ssmits

·

AI & ML interests

Synthetic data, on-premise / local language-specific LLMs, optimizing embeddings models retrieval

Recent Activity

upvoted an article 2 days ago

Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face

liked a model 3 days ago

arcee-ai/AFM-4.5B-Base

liked a model 3 days ago

arcee-ai/AFM-4.5B

View all activity

Organizations

Collections 3

View 3 collections

models 67

ssmits/Qwen2.5-7B-embed-base

Text Classification • 7B • Updated Jan 18 • 18 • 1

ssmits/Qwen2.5-7B-Instruct-embed-base

Text Classification • 7B • Updated Jan 18 • 51 • 1

ssmits/ModernBERT-base-dutch-test

0.1B • Updated Dec 22, 2024 • 4 • 1

ssmits/Qwen2-7B-embed-base

Feature Extraction • 7B • Updated Nov 24, 2024 • 7

ssmits/Zamba2-1.2B

1B • Updated Nov 6, 2024 • 3

ssmits/Zamba2-1.2B-instruct-Dutch

Text Generation • 1B • Updated Nov 3, 2024 • 13 • 1

ssmits/Llama-3.1-Nemotron-92B-Instruct-HF-late-GGUF

Updated Nov 1, 2024

ssmits/Llama-3.1-Nemotron-92B-Instruct-HF-early-GGUF

Updated Nov 1, 2024

ssmits/Llama-3.1-Nemotron-92B-Instruct-HF-late

Text Generation • 92B • Updated Nov 1, 2024 • 7 • 2

ssmits/Llama-3.1-Nemotron-92B-Instruct-HF-early

Text Generation • 92B • Updated Nov 1, 2024 • 10 • 2

datasets 6

ssmits/fineweb-2-dutch

Viewer • Updated Dec 20, 2024 • 83.5M • 749 • 2

ssmits/processed-falcon-dutch-dataset

Viewer • Updated Nov 3, 2024 • 450k • 204

ssmits/tokenized-falcon2-dutch-2048

Viewer • Updated Nov 3, 2024 • 1.91M • 324

ssmits/tokenized-llama3-dutch-2048

Viewer • Updated Nov 3, 2024 • 1.27M • 339

ssmits/tokenized-falcon2-dutch-4096

Viewer • Updated Nov 3, 2024 • 1.05M • 239

ssmits/small-test-dataset

Viewer • Updated Jul 15, 2024 • 21.8k • 5