lumma-fev

Run FrontiersMind Lumma-Fev decision models: give a document (the state) and typed questions, and get a probability distribution for every question in one forward pass. No text is generated, so there is nothing to parse.

• lumma_fev.load(): run a model locally (cuda, mps or cpu).
• lumma-fev-serve: a TypeSafe-compatible HTTP API (POST /v1/systemone), so existing TypeSafe clients work by changing their base URL.
• lumma_fev.Client: a small client for that API.

Models: FrontiersMind/lumma-fev-0.1b (default) and other FrontiersMind/lumma-fev-* repos.

Install

pip install lumma-fev              # local inference and the client
pip install "lumma-fev[serve]"     # plus the API server

Run locally

import lumma_fev

model = lumma_fev.load()           # FrontiersMind/lumma-fev-0.1b; load("FrontiersMind/<repo>", revision=...) for others

answers = model.decide(
    state="I was charged twice for my March invoice. Please refund one of them.",
    questions={
        "billing": {"type": "noul", "instructions": "Is this about billing?"},
        "team": {"type": "choice", "instructions": "Which team should handle this?",
                 "criteria": {"billing": "Payments and refunds", "shipping": "Delivery problems", "technical": "Bugs and outages"}},
        "urgency": {"type": "score", "instructions": "How urgent is this?",
                    "criteria": ["can wait", "this week", "today"]},
    },
)
# {"billing": {"noul": 0.97}, "team": {"choice": "billing", "confidence": ..., "probabilities": {...}},
#  "urgency": {"score": ..., "confidence": ..., "legend": [...], "probabilities": {...}}}

load(model, revision=None, device=None, dtype=None) picks cuda, then mps, then cpu, and uses bf16 on accelerators and fp32 on cpu. The same model loads with transformers alone: AutoModel.from_pretrained("FrontiersMind/lumma-fev-0.1b", trust_remote_code=True).

Serve an API

lumma-fev-serve --model FrontiersMind/lumma-fev-0.1b --host 0.0.0.0 --port 8000

Endpoints: POST /v1/systemone, GET /v1/models, GET /health. Requests run one at a time.

curl -s localhost:8000/v1/systemone -H 'content-type: application/json' -d '{
  "state": "I was charged twice. Please fix this ASAP.",
  "questions": {"billing": {"type": "noul", "instructions": "Is this ticket about billing?"}}
}'
# {"model": "lumma-fev-latest", "answers": {"billing": {"noul": 0.98}}, "usage": {"input_tokens": 31, "output_tokens": 9}}

Call it from Python

from lumma_fev import Client

with Client("http://127.0.0.1:8000", api_key=None) as client:
    print(client.decide("I was charged twice.", {"billing": {"type": "noul", "instructions": "Is this about billing?"}}))
    print(client.models())

client.system_one(...) returns the full response (model, answers, usage); errors raise lumma_fev.LummaFevError with the HTTP status and detail.

The TypeSafe SDK works against the same server:

from typesafe_sdk import Noul, TypeSafeClient

with TypeSafeClient(api_key="local", base_url="http://127.0.0.1:8000") as ts:
    result = ts.system_one(state="I was charged twice.", questions={"billing": Noul(instructions="Is this about billing?")})
    print(result.nouls["billing"].noul)

The SDK always sends an API key; any value works when the server has no --api-key.

Questions and answers

state and instructions can be text or any JSON value. Each question reads the state and its own instructions and options only, so questions never influence each other. Long states are truncated to the model's context (see the model card).

License

Apache-2.0. See LICENSE and NOTICE.