Xorbits Inference (Xinference)

%pip install -qU  "xinference[all]"

!xinference launch -n vicuna-v1.3 -f ggmlv3 -q q4_0

Model uid: 7167b2b0-2a04-11ee-83f0-d29396a3f064

from langchain_community.llms import Xinference

llm = Xinference(
    server_url="http://0.0.0.0:9997", model_uid="7167b2b0-2a04-11ee-83f0-d29396a3f064"
)

llm(
    prompt="Q: where can we visit in the capital of France? A:",
    generate_config={"max_tokens": 1024, "stream": True},
)

' You can visit the Eiffel Tower, Notre-Dame Cathedral, the Louvre Museum, and many other historical sites in Paris, the capital of France.'

from langchain.chains import LLMChain
from langchain_core.prompts import PromptTemplate

template = "Where can we visit in the capital of {country}?"

prompt = PromptTemplate.from_template(template)

llm_chain = LLMChain(prompt=prompt, llm=llm)

generated = llm_chain.run(country="France")
print(generated)

A: You can visit many places in Paris, such as the Eiffel Tower, the Louvre Museum, Notre-Dame Cathedral, the Champs-Elysées, Montmartre, Sacré-Cœur, and the Palace of Versailles.

!xinference terminate --model-uid "7167b2b0-2a04-11ee-83f0-d29396a3f064"