Pruned Falcon-11B variant optimized for 13 European languages through layer selection.
S. Smits
ssmits
AI & ML interests
Synthetic data, on-premise / local language-specific LLMs, optimizing embeddings models retrieval
Recent Activity
upvoted
an
article
3 days ago
Fine-tune ModernBERT for text classification using synthetic data
liked
a model
6 days ago
jinaai/jina-embeddings-v3
liked
a model
10 days ago
deepseek-ai/DeepSeek-V3-Base
Organizations
Collections
3
models
67
ssmits/ModernBERT-base-dutch-test
Updated
•
16
•
1
ssmits/Qwen2.5-7B-embed-base
Updated
•
10
ssmits/Qwen2.5-7B-Instruct-embed-base
Updated
•
14
•
1
ssmits/Qwen2-7B-embed-base
Feature Extraction
•
Updated
•
24
ssmits/Zamba2-1.2B
Updated
•
5
ssmits/Zamba2-1.2B-instruct-Dutch
Text Generation
•
Updated
•
23
ssmits/Llama-3.1-Nemotron-92B-Instruct-HF-late-GGUF
Updated
ssmits/Llama-3.1-Nemotron-92B-Instruct-HF-early-GGUF
Updated
ssmits/Llama-3.1-Nemotron-92B-Instruct-HF-late
Text Generation
•
Updated
•
124
•
2
ssmits/Llama-3.1-Nemotron-92B-Instruct-HF-early
Text Generation
•
Updated
•
80
•
2
datasets
6
ssmits/fineweb-2-dutch
Viewer
•
Updated
•
83.5M
•
310
•
2
ssmits/processed-falcon-dutch-dataset
Viewer
•
Updated
•
450k
•
339
ssmits/tokenized-falcon2-dutch-2048
Viewer
•
Updated
•
1.91M
•
374
ssmits/tokenized-llama3-dutch-2048
Viewer
•
Updated
•
1.27M
•
512
ssmits/tokenized-falcon2-dutch-4096
Viewer
•
Updated
•
1.05M
•
203
ssmits/small-test-dataset
Viewer
•
Updated
•
21.8k
•
41