metadata
license: other
datasets:
- georgesung/wizard_vicuna_70k_unfiltered
Overview
Fine-tuned Llama-3 8B with an uncensored/unfiltered Wizard-Vicuna conversation dataset. Used QLoRA for fine-tuning.
The model here includes the fp32 HuggingFace version, plus a quantized 4-bit q4_0 gguf version.
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?
...
Training code
Code used to train the model is available here.
To reproduce the results:
git clone https://github.com/georgesung/llm_qlora
cd llm_qlora
pip install -r requirements.txt
python train.py configs/llama3_8b_chat_uncensored.yaml