Hugging Face's logo

edwindn
/
Deepseek-R1-Llama-8B-lazy-v0.1

Safetensors
Model card Files
xet
Community

Finetune of DeepSeek-R1 Llama-3-8B distil

  • Dataset: lazy_1 + lazy_2 + lazy_3
  • Dataset size: 300 samples
  • Epochs: 10
  • Samples with answer: 100%

Little to no change from default behaviour on OOD data, good change on ID data.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support