metadata
base_model: safe049/Ruozhiba_llama3
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
- sft
datasets:
- neifuisan/Neuro-sama-QnA
Uploaded model
- Developed by: safe049
- License: apache-2.0
- Finetuned from model : safe049/Ruozhiba_llama3
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
Informations
This model is uncensored and based on Undi95/Llama-3-LewdPlay-8B which is uncensored. It is not fully uncensored,you need a prompt like dolphin or something else to fully uncensor it
Trained on Google Colab
Just for boring,Using prompt from Github repository: https://github.com/kimjammer/Neuro/blob/master/Neuro.yaml
Trained with Ruozhiba Dataset,so it have fantastic Chinese conversation ability and good logical thinks
Use
Just see the "use the model" in this page
I'm using the Q4KM GGUF in ollama.