FROM registry.cn-shanghai.aliyuncs.com/modelscope-repo/modelscope:fc-deploy-common-v17

WORKDIR /usr/src/app

COPY . .

RUN pip install -U transformers

CMD [ "python3", "-u", "/usr/src/app/app.py" ]

EXPOSE 9000

from flask import Flask, request
from transformers import AutoTokenizer, AutoModelForCausalLM

model_dir = '/usr/src/app/gemma-2b-it'

app = Flask(__name__)

tokenizer = AutoTokenizer.from_pretrained(model_dir)
model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto")

@app.route('/invoke', methods=['POST'])
def invoke():
    # See FC docs for all the HTTP headers: https://help.aliyun.com/document_detail/179368.html#section-fk2-z5x-am6
    request_id = request.headers.get("x-fc-request-id", "")
    print("FC Invoke Start RequestId: " + request_id)

    text = request.get_data().decode("utf-8")
    print(text)
    input_ids = tokenizer(text, return_tensors="pt").to("cuda")
    outputs = model.generate(**input_ids, max_new_tokens=1000)
    response = tokenizer.decode(outputs[0])
    print("FC Invoke End RequestId: " + request_id)
    return str(response) + "\n"

if __name__ == '__main__':
    app.run(debug=False, host='0.0.0.0', port=9000)

.
|-- app.py
|-- Dockerfile
`-- gemma-2b-it
    |-- config.json
    |-- generation_config.json
    |-- model-00001-of-00002.safetensors
    |-- model-00002-of-00002.safetensors
    |-- model.safetensors.index.json
    |-- README.md
    |-- special_tokens_map.json
    |-- tokenizer_config.json
    |-- tokenizer.json
    `-- tokenizer.model

1 directory, 12 files

IMAGE_NAME=registry.cn-shanghai.aliyuncs.com/{NAMESPACE}/{REPO}:gemma-2b-it
docker build -f Dockerfile -t $IMAGE_NAME . && docker push $IMAGE_NAME

curl -X POST -d "who are you" https://gemma-service-xxx.cn-shanghai.fcapp.run/invoke
<bos>who are you?

I am a large language model, trained by Google. I am a conversational AI that can understand and generate human language, and I am able to communicate and provide information in a comprehensive and informative way.

What can I do for you today?<eos>