【书生大模型实战营_第6期】基础岛第3关_L1 Intern-S1-mini 本地部署实践 简单

conda create -n lmdeploy python=3.10 -y
conda activate lmdeploy
pip install "lmdeploy==0.9.2.post1" "transformers==4.55.2"

lmdeploy serve api_server /root/share/new_models/Intern-S1-mini \
    --reasoning-parser intern-s1 \
    --tool-call-parser intern-s1 \
    --cache-max-entry-count 0.1 \
    --max-batch-size 8 \
    --backend turbomind \
    --session-len 2048

from openai import OpenAI
import json

messages = [
{
    'role': 'user',
    'content': 'who are you'
}, {
    'role': 'assistant',
    'content': 'I am an AI'
}, {
    'role': 'user',
    'content': 'AGI is?'
}]

openai_api_key = "EMPTY"
openai_api_base = "http://0.0.0.0:23333/v1"
client = OpenAI(
    api_key=openai_api_key,
    base_url=openai_api_base,
)
model_name = client.models.list().data[0].id

response = client.chat.completions.create(
    model=model_name,
    messages=messages,
    temperature=0.8,
    top_p=0.8,
    max_tokens=2048,
    extra_body={
        "enable_thinking": False,
    }
)
print(json.dumps(response.model_dump(), indent=2, ensure_ascii=False))