Configuration Parsing Warning:In adapter_config.json: "peft.task_type" must be a string

jeff-adapter-spam

Spam and phishing detection. Detects spam or phishing in text messages and emails. A separate function classifies each message as legitimate, spam or phishing.

A LoRA adapter for jeff-base v1.4, Jeff's small open decision model (a fine-tune of Qwen3.5-0.8B). You give it a situation and a question with named options; it returns a calibrated probability for every option from one forward pass, with no generated text to parse.

When to use it

  • You need spam and phishing probabilities for incoming text messages or emails.
  • You need to distinguish advertising spam from scams seeking personal details, passwords or money.

When not to use it

  • You need to inspect email headers, links or attachments; this adapter reads only the subject and readable body.
  • You need a definitive blocking decision without human review; use the prediction as one input to that decision.

What it decides

What a call sends:

Field Required What it holds
channel (context) yes Where the message came from: "sms" or "email", as in training.
message (input, fields) yes The text of the message as received. For an email, its subject and readable body (no other headers, no attachments).

jeff.safety.spam.is_spam (detect, noul)

Instructions: Is this message spam or phishing? Answer yes if it is unwanted bulk or advertising, or a scam trying to get personal details or money; answer no if it is a normal message.

Labels:

  • false: The message is a normal message: not unwanted bulk or advertising, and not a scam.
  • true: The message is spam (unwanted bulk or advertising) or phishing (a scam trying to get personal details, passwords or money).

jeff.safety.spam.message_type (classify, choice)

Instructions: What kind of message is this: a legitimate message, spam (unwanted bulk or advertising), or phishing (a scam trying to get personal details, passwords or money)?

Labels:

  • legitimate: A normal message from a person or a genuine organisation, not spam and not phishing.
  • phishing: A scam message that tries to trick the reader into giving personal details, passwords or money, often by pretending to be a bank, company or authority and asking them to click a link or call a number.
  • spam: Unwanted bulk or advertising message (for example prizes, offers, premium-rate services), but not trying to steal personal or account details.

How it was measured

Base: Jeff v1.4; adapter trained 2026-10-25.

Test Rows Accuracy
real messages from public spam and phishing collections (SMS and email) (public) 3,897 98.4%
the test set of the earlier version (public) 3,603 98.3%

Accuracy is the share of test rows whose top answer was right. Kinds: public, a public benchmark; real, held-out real documents; generator, an in-house test from the same generator as the training data (it measures less than a public or real test does); mixed, several kinds; unknown, not recorded.

When it is confident (from the calibration set): the threshold is the confidence from which an answer counts as confident, precision the share of confident answers that were right, coverage the share of answers that were confident.

Function Threshold Precision Coverage Calibration rows
is_spam 0.516 99.2% 100.0% 1,113
message_type 0.426 98.1% 100.0% 832

How to call it

Install the Python SDK and the engine (see the install guide; until the packages are on PyPI, install them from github.com/firelex/jeff).

The example below is "Parcel redelivery fee text". A message asking for a small fee through an unknown link is after money or details, so it is phishing.

On your machine (Jeff.local downloads this adapter and the base from Hugging Face the first time):

import jeff

client = jeff.Jeff.local(["spam"])

decide = client.function("jeff.safety.spam.message_type", context={
    "channel": "sms",
})

decision = decide("Your parcel could not be delivered. Pay the 1.99 redelivery fee within 24 hours here: http://parcel-redeliver.example/pay")

print(decision.value, decision.confidence)

Through the Jeff API (an API key from jeffhub.ai):

import os

import jeff

with jeff.Jeff.remote("https://api.jeffhub.ai", token=os.environ["JEFF_API_KEY"], timeout_s=30) as client:
    decide = client.function("jeff.safety.spam.message_type", context={
        "channel": "sms",
    })

    decision = decide("Your parcel could not be delivered. Pay the 1.99 redelivery fee within 24 hours here: http://parcel-redeliver.example/pay")

    print(decision.value, decision.confidence)
curl -s https://api.jeffhub.ai/v1/decide \
  -H "Authorization: Bearer $JEFF_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"calls": [{"function": "jeff.safety.spam.message_type", "input": "Your parcel could not be delivered. Pay the 1.99 redelivery fee within 24 hours here: http://parcel-redeliver.example/pay", "context": {"channel": "sms"}}]}'

Recorded answer (2026-11-03): phishing with confidence 0.911.

To download the weights yourself:

hf download mstrasser/jeff-base --revision v1.4 --local-dir jeff-base
hf download mstrasser/jeff-adapter-spam --revision v1.4 --local-dir adapters/spam

Files

File What it is
adapter_model.safetensors, adapter_config.json The LoRA weights and their configuration
readout.safetensors The adapter's readout over the answer codes
decision_config.json Answer codes, temperature, prompt layout and the base it was trained on (the SHA-256 of the base's weights, which the engine checks)
manifest.yaml The adapter's manifest: its functions, labels, fields and calibration, as the SDKs read it
test.jsonl The held-out test set the numbers above come from
calibration.jsonl The calibration set the thresholds come from
LICENSE The Apache License 2.0, for the Qwen3.5-0.8B notice below

Licence

Adapter licence: Apache-2.0

Qwen3.5-0.8B notice: these weights were modified from Qwen3.5-0.8B by the Jeff project: jeff-base is a fine-tune of Qwen3.5-0.8B, and this adapter was trained on top of it. Qwen3.5-0.8B is Copyright 2026 Alibaba Cloud and licensed under the Apache License, Version 2.0; a copy of that licence is in LICENSE.

Jeff is an independent project, not affiliated with or endorsed by the makers of Qwen.

Downloads last month
65
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for mstrasser/jeff-adapter-spam

Adapter
(34)
this model