Uploaded model

  • Developed by: duxx
  • License: apache-2.0
  • Finetuned from model : duxx/test_model_16bit_50

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month
56
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

Model tree for duxx/test_model_16bit_50_dpo

Finetuned
(1)
this model