CarlOwOs
/

distilled-qwen3-0.6b-full-mmlu

Text Generation

knowledge-distillation

full-fine-tuning

text-generation-inference

Model card Files Files and versions

Metrics Training metrics Community

distilled-qwen3-0.6b-full-mmlu / runs /Jun02_08-36-00_mem-0-0

4.98 kB

1 contributor

History: 1 commit

CarlOwOs's picture

Upload distilled Qwen model (Full) - α=0.7, T=4.0

160d925 verified 6 months ago

events.out.tfevents.1748853361.mem-0-0

4.98 kB
xet

Upload distilled Qwen model (Full) - α=0.7, T=4.0 6 months ago