stephenlzc/Gemma-2-9B-Chinese-Chat-Uncensored

Model Details

Model Description

• Using shenzhi-wang/Gemma-2-9B-Chinese-Chat as base model, and finetune the dataset as mentioned via unsloth. Makes the model uncensored.
• 

Training Code and Log

• ipynb file

Training Procedure Raw Files

• ALL the procedure are training on Runpod.io

• Hardware in Vast.ai:

  • GPU: 1 x A100 SXM 80G

  • CPU: 16vCPU

  • RAM: 251 GB

  • Disk Space To Allocate：>150GB

  • Docker Image: runpod/pytorch:2.2.0-py3.10-cuda12.1.1-devel-ubuntu22.04

Training Data

• Base Model

  • shenzhi-wang/Gemma-2-9B-Chinese-Chat

• Dataset

  • V3N0M/Jenna-50K-Alpaca-Uncensored

Usage

from transformers import pipeline

qa_model = pipeline("question-answering", model='stephenlzc/Gemma-2-9B-Chinese-Chat-Uncensored')
question = "How to make girlfreind laugh? please answer in Chinese."
qa_model(question = question)