Back to Mistral Rs

topology

docs/src/content/docs/examples/python/topology.md

0.8.10941 B
Original Source
<!-- generated by docs/scripts/render_examples.py; edit the source example instead -->

Runnable Python SDK example topology.

<!-- needs-header -->
python
from mistralrs import Runner, Which, ChatCompletionRequest, Architecture

runner = Runner(
    which=Which.Plain(
        model_id="mistralai/Mistral-7B-Instruct-v0.1",
        arch=Architecture.Mistral,
        topology="topologies/isq.yml",
    ),
    in_situ_quant="Q4K",
)

res = runner.send_chat_completion_request(
    ChatCompletionRequest(
        model="default",
        messages=[
            {"role": "user", "content": "Tell me a story about the Rust type system."}
        ],
        max_tokens=256,
        presence_penalty=1.0,
        top_p=0.1,
        temperature=0.1,
    )
)
print(res.choices[0].message.content)
print(res.usage)

Source: examples/python/topology.py