digitalpipelines commited on
Commit
230f84a
1 Parent(s): 64a8470

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -21,7 +21,7 @@ tags:
21
 
22
  # Overview
23
  Fine-tuned [Llama-2 13B](https://huggingface.co/TheBloke/Llama-2-13B-Chat-fp16) trained with an uncensored/unfiltered Wizard-Vicuna conversation dataset [digitalpipelines/wizard_vicuna_70k_uncensored](https://huggingface.co/datasets/digitalpipelines/wizard_vicuna_70k_uncensored).
24
- QLoRA was used for fine-tuning.
25
 
26
 
27
  ## Available versions of this model
 
21
 
22
  # Overview
23
  Fine-tuned [Llama-2 13B](https://huggingface.co/TheBloke/Llama-2-13B-Chat-fp16) trained with an uncensored/unfiltered Wizard-Vicuna conversation dataset [digitalpipelines/wizard_vicuna_70k_uncensored](https://huggingface.co/datasets/digitalpipelines/wizard_vicuna_70k_uncensored).
24
+ A QLoRA was created and used for fine-tuning and then merged back into the model. Llama2 has inherited bias even though it's been finetuned on an uncensored dataset.
25
 
26
 
27
  ## Available versions of this model