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
Base model
unsloth/tinyllama-bnb-4bit
Finetuned
duxx/test_model_16bit_25
Finetuned
duxx/test_model_16bit_50