metadata
datasets:
- unalignment/toxic-dpo-v0.1
llama2_xs_460M_uncensored
Model Details
llama2_xs_460M_experimental DPO finedtuned to remove alignment (3 epochs QLoRa).
Model Description
- Developed by: Harambe Research
- Model type: llama2
- Finetuned from model: llama2_xs_460M_experimental
Out-of-Scope Use
Don't use this to do bad things. Bad things are bad.
Recommendations
Users (both direct and downstream) should be aware of the risks, biases and limitations of the model.