State-of-the-art Danish Models
Collection
These models constitute state-of-the-art models for Danish within their respective domain (highlighted below the model).
•
18 items
•
Updated
•
18
Rasmus Aagaard
rasgaard
AI & ML interests
Industrial PhD student, research on model compression techniques and efficient on-device inference
Recent Activity
liked
a Space
about 20 hours ago
KevinAHM/pocket-tts-web
upvoted
a
collection
about 21 hours ago
State-of-the-art Danish Models
upvoted
an
article
1 day ago
Slashing torch.compile Warmup & LoRA Swapping Times with Pruna
Organizations
upvoted
a
collection
about 21 hours ago
upvoted
2
articles
1 day ago
Article
Slashing torch.compile Warmup & LoRA Swapping Times with Pruna
•
4
Article
We Got Claude to Build CUDA Kernels and teach open models!
- +2
•
82
upvoted
a
collection
3 days ago
upvoted
an
article
about 1 month ago
Article
Tokenization in Transformers v5: Simpler, Clearer, and More Modular
- +4
•
119
upvoted
3
articles
2 months ago
Article
Curating datasets directly on the Hub
•
22
Article
Continuous batching from first principles
- +1
•
313
Article
AI Model Optimization More Flexible Than Ever
•
13
upvoted
3
articles
3 months ago
Article
Running Large Transformer Models on Mobile and Edge Devices
•
13
Article
Streaming datasets: 100x More Efficient
- +3
•
80
Article
Sentence Transformers is joining Hugging Face!
•
87
upvoted
3
articles
4 months ago
Article
Get your VLM running in 3 simple steps on Intel CPUs
- +3
•
22
Article
SOTA OCR with Core ML and dots.ocr
•
62
Article
There is no such thing as a tokenizer-free lunch
•
95
upvoted
a
paper
4 months ago
upvoted
an
article
5 months ago
Article
KV Caching Explained: Optimizing Transformer Inference Efficiency
•
224
upvoted
a
paper
5 months ago
upvoted
an
article
8 months ago
Article
AI Policy @🤗: Response to the 2025 National AI R&D Strategic Plan
•
14
upvoted
a
collection
8 months ago
upvoted
an
article
9 months ago
Article
Blazingly fast whisper transcriptions with Inference Endpoints
- +4
•
81