metadata
license: apache-2.0
datasets:
- digitalpipelines/wizard_vicuna_70k_uncensored
Overview
Fine-tuned OpenLLaMA-7B with an uncensored/unfiltered Wizard-Vicuna conversation dataset digitalpipelines/wizard_vicuna_70k_uncensored. Used QLoRA for fine-tuning using the process outlined in https://georgesung.github.io/ai/qlora-ift/
A quantized GPTQ model can be found at digitalpipelines/llama2_7b_chat_uncensored-GPTQ
Prompt style
The model was trained with the following prompt style:
### HUMAN:
Hello
### RESPONSE:
Hi, how are you?
### HUMAN:
I'm fine.
### RESPONSE:
How can I help you?
...