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

jeff-adapter-support-intents

Customer request classification. Identifies the request in a customer or assistant-user message, choosing from a fixed list such as cancel_order or track_refund.

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 to classify requests in an online shop chat or voice assistant.
  • Messages are short and in English.

When not to use it

  • You need to identify every request in a message containing several; this adapter selects one.
  • Your inputs are long emails or tickets; use Support ticket triage.

What it decides

What a call sends:

Field Required What it holds
service (context) yes One short phrase about the service the message is sent to. Training used three, one per data set, for example "Customer support chat of an online shop".
message (input, fields) yes The customer's or user's message as received.

jeff.support.support-intents.intent (classify, choice)

Instructions: What does the customer want? Choose the request that best matches what the customer is asking for in their message.

Labels:

  • The caller gives the labels (at most 64), each a key and its text.

How it was measured

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

Test Rows Accuracy
public intent data sets: Bitext customer support, HWU64 and SNIPS (public) 5,577 96.4%

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
intent 0.290 96.5% 100.0% 999

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 "Cancel boots before they ship". The boots have not shipped yet, so the customer's request is cancel_order.

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

import jeff

client = jeff.Jeff.local(["support-intents"])

decide = client.function("jeff.support.support-intents.intent", context={
    "service": "Customer support chat of an online shop",
}, labels={
    "cancel_order": "Cancel an order that has not been delivered yet",
    "track_order": "Find out where an order is",
    "change_address": "Change the delivery address of an order",
    "return_item": "Return an item that was delivered",
    "track_refund": "Find out the status of a refund",
})

decision = decide("hi, i changed my mind about the boots i ordered yesterday, can i still stop the order before it ships?")

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.support.support-intents.intent", context={
        "service": "Customer support chat of an online shop",
    }, labels={
        "cancel_order": "Cancel an order that has not been delivered yet",
        "track_order": "Find out where an order is",
        "change_address": "Change the delivery address of an order",
        "return_item": "Return an item that was delivered",
        "track_refund": "Find out the status of a refund",
    })

    decision = decide("hi, i changed my mind about the boots i ordered yesterday, can i still stop the order before it ships?")

    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.support.support-intents.intent", "input": "hi, i changed my mind about the boots i ordered yesterday, can i still stop the order before it ships?", "context": {"service": "Customer support chat of an online shop"}, "labels": {"cancel_order": "Cancel an order that has not been delivered yet", "track_order": "Find out where an order is", "change_address": "Change the delivery address of an order", "return_item": "Return an item that was delivered", "track_refund": "Find out the status of a refund"}}]}'

Recorded answer (2026-11-03): cancel_order with confidence 0.999.

To download the weights yourself:

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

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
89
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for mstrasser/jeff-adapter-support-intents

Adapter
(34)
this model