README.md

metadata

license: mit

Introduction

The repository consists of the weights of Finetuned Qwen2.5-7B, the scripts you need, the datasets we use to finetune the base model.

-whole_data_v2.json includes all the data we use
-varify_yaoying_knowledge.json includes only general knowledge about Yaoying
-mix_yaoying_paradigm.json is composed of different types of knowledge, with paradigm accounting for 80% and general knowledge about Yaoying accounting for 20%

Installation

Before you start, make sure you have installed the following packages: Environment:Python=3.10, CUDA=11.8, gcc > 9

pip install -r requirements.txt --extra-index-url https://download.pytorch.org/whl/cu118

Quickstart

If you want to inference with vllm,

python with_vllm.py
# You can change prompt in the script

If you want to test the model without vllm,

python inference_without_vllm.py
# You can change prompt in the script