Xiaomi MiMo
Xiaomi MiMo
https://platform.xiaomimimo.com/#/docs
모든 Xiaomi MiMo 모델을 지원해요. LiteLLM 요청 시
model=xiaomi_mimo/<any-model-on-xiaomi-mimo>처럼 접두어로xiaomi_mimo/를 붙이면 돼요.
API 키 (API Key)
# env variable
os.environ['XIAOMI_MIMO_API_KEY']
샘플 사용법 (Sample Usage)
from litellm import completion
import os
os.environ['XIAOMI_MIMO_API_KEY'] = ""
response = completion(
model="xiaomi_mimo/mimo-v2-flash",
messages=[
{
"role": "user",
"content": "What's the weather like in Boston today in Fahrenheit?",
}
],
max_tokens=1024,
temperature=0.3,
top_p=0.95,
)
print(response)
샘플 사용법 - 스트리밍 (Sample Usage - Streaming)
from litellm import completion
import os
os.environ['XIAOMI_MIMO_API_KEY'] = ""
response = completion(
model="xiaomi_mimo/mimo-v2-flash",
messages=[
{
"role": "user",
"content": "What's the weather like in Boston today in Fahrenheit?",
}
],
stream=True,
max_tokens=1024,
temperature=0.3,
top_p=0.95,
)
for chunk in response:
print(chunk)
LiteLLM Proxy Server와 함께 사용하기 (Usage with LiteLLM Proxy Server)
LiteLLM Proxy Server로 Xiaomi MiMo 모델을 호출하는 방법이에요.
- config.yaml 수정:
model_list:
- model_name: my-model
litellm_params:
model: xiaomi_mimo/<your-model-name> # add xiaomi_mimo/ prefix to route as Xiaomi MiMo provider
api_key: api-key # api key to send your model
- 프록시 시작:
$ litellm --config /path/to/config.yaml
-
LiteLLM Proxy Server에 요청 보내기:
-
OpenAI Python v1.0.0+
-
curl
import openai
client = openai.OpenAI(
api_key="sk-<your-litellm-api-key>", # pass litellm proxy key, if you're using virtual keys
base_url="http://0.0.0.0:4000" # litellm-proxy-base url
)
response = client.chat.completions.create(
model="my-model",
messages = [
{
"role": "user",
"content": "what llm are you"
}
],
)
print(response)
curl --location 'http://0.0.0.0:4000/chat/completions' \
--header "Authorization: Bearer ***" \
--header 'Content-Type: application/json' \
--data '{
"model": "my-model",
"messages": [
{
"role": "user",
"content": "what llm are you"
}
],
}'
지원 모델 (Supported Models)
| 모델명 | 사용법 |
|---|---|
mimo-v2-flash |
completion(model="xiaomi_mimo/mimo-v2-flash", messages) |
출처: 문서