Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
jquad
/
DeepSeek-R1-0528-Qwen3-8B-German-GRPO
like
2
Safetensors
German
grpo
lora
german
math-reasoning
deepseek
unsloth
License:
apache-2.0
Model card
Files
Files and versions
Community
main
DeepSeek-R1-0528-Qwen3-8B-German-GRPO
/
adapter_model.safetensors
Commit History
Upload LoRA adapters (Trained with Unsloth)
8cce8b8
verified
jquad
commited on
25 days ago
Upload model trained with Unsloth
b91a323
verified
jquad
commited on
25 days ago