45 lines
1.2 KiB
Markdown
45 lines
1.2 KiB
Markdown
|
---
|
||
|
|
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](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
||
|
|
|
||
|
|
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
||
|
|
|
||
|
|
# 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.
|