PEFT
Safetensors
llama
Generated from Trainer
4-bit precision
bitsandbytes

Fine-tuned version of cognitivecomputations/Dolphin3.0-Llama3.2-3B on the ICEPVP8977/Uncensored_Small_Test_Time_Compute dataset.

This LoRA will fully uncensor the Dolphin3.0-Llama3.2-3B, use alpaca instruction template.

Downloads last month
5
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for vpakarinen/dolphin-llama-3b-lora-uncensored

Adapter
(2)
this model

Dataset used to train vpakarinen/dolphin-llama-3b-lora-uncensored

Collection including vpakarinen/dolphin-llama-3b-lora-uncensored