c74d76954f
And add a proxy service interface, Integrate Swift with fastapi_cient py The client can directly use fastapi_cient Py doesn't need to be changed
2.0 KiB
0 . Fine tuning restrictions
Fine tuning supports training for image understanding but not image generation
1. install ms-swift
use ms-swift Fine tune the Janus-Pro-7B model, First, install ms-swift
pip install git+https://github.com/modelscope/ms-swift.git cd ms-swift pip install -e .
2. Datasets
The dataset format is {"messages": [{"role": "user", "content": "Does the construction worker in this picture comply with the safety regulations for high-altitude operations？"}, {"role": "assistant", "content": "In the high-altitude work area, people entering the construction site must wear safety helmets, and high-altitude workers should wear safety belts. The other end of the safety belt must be hung higher than the human body, which is called high hanging and low use. The high-altitude workers in the picture did not wear safety belts, which does not meet the safety standards for high-altitude operations."}], "images": ["root/train/train_images/wpd-36.jpg"]}
3. Fine tuning
lora Fine tuning swift sft --model_type deepseek_janus_pro --model --dataset --target_modules all-linear
full Fine tuning swift sft --model_type deepseek_janus_pro --model --dataset --train_type full
4. swift model Service
swift deploy --ckpt_dir
5. swift model Proxy Service
fastapi_swift.py
6. Client API fastapi_client. py
Submit questions and receive responses to the swift model Proxy Service using fastapi_client. py
Other1.
The parameters(seed、top_p、temperature ) are no longer useful, but in order to maintain interface reuse, they are retained
Other2.
If the Swift model needs to change the directory, the configuration file needs to be changed Adapterconfig.json Modify 'base_madel_name_or_path' Args.json modifies 'model' Specify the Janus-Pro-7B directory for classical gravity