Hugging Face's logo

tahamajs
/
Qwen3-4b-gsm8k-Qlora-GRPO

Text Generation
PEFT
Safetensors
Transformers
English
grpo
lora
trl
unsloth
qwen3
bitsandbytes
4bit
conversational
Model card Files
xet
Community
Qwen3-4b-gsm8k-Qlora-GRPO / merges.txt

Commit History

Continue training: +5k steps on extra math data
f16a61e
verified

tahamajs commited on