No official torrent yet β requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from inclusionAI/LemonDecider
All models by inclusionAI βModel ID: lemondecider-4b-20261023-v3
Base model: Qwen/Qwen3.5-4B
This v3 release makes typed decisions from a shared text state and named questions.
It returns choice probabilities, yes/no probabilities (noul), or ordinal scores
without generating an answer token stream. Requests that fit use one joint forward;
overlength question lists are recursively bisected, preserving the complete state
and every option in each chunk. Inputs are never truncated.
LemonDecider 4B v3 was fine-tuned (SFT) from a common Qwen3.5-4B initialization on 1,199,692 decision/QA rows (about 1.20M training rows, with separate development, calibration and test splits). The released weights are a uniform FP32 average of four checkpoints from the same SFT run, followed by scalar temperature calibrationβnot a combination of two independent training runs.
Question formats: choice (up to 255 options; 84.4%), noul (no/yes; 15.2%) and score (ordinal ratings; 0.4%). This training run is text-only, with the vision tower frozen. The original training corpus retains joint-question grouping where applicable; the single-record export preserves the question-level content but removes grouping metadata and is not an exact reproduction of the original joint-training layout.
Data categories:
Training parameters (from the recorded configuration and training log):
option_cross_entropy; choice permutation global-reference; text-only inputs and frozen vision tower;fp32-master-bf16, BF16 serving load, SDPA with noncausal full attention;The corpus manifest records fingerprint-based filtering against protected JevBench and Decision Index evaluation inputs, while some source collections include benchmark training splits. This is not a blanket guarantee of zero overlap, nor a claim that every upstream source has permissive redistribution terms; source-specific terms still require review.
The repository keeps the model/processor/tokenizer filenames used by the HF
layout. v3 additionally requires joint_readout.py; code/ provides the serving
entry points, and requirements.txt describes installation dependencies.
Original copyright and license notices are retained.
On 2026-10-25, the chunked service performed a fresh full evaluation over
140,178 scoreable requests using four independent PPU-ZW810E workers. The 442
officially excluded requests were filtered before inference. The official scorer
reported complete: true, with 140,148 ok and 30 unsupported.
This is a self-evaluated public-suite result, not an official private Full score or
leaderboard acceptance. Latency is HTTP request wall time from a four-worker PPU
run, not official single-GPU latency admission. Kit commit:
25c6ec7b6b5f44a216c63c3a700de3a9c6d6699d.
$0
The Score column uses each benchmark's native summary metric on supported cases; Skill and Coverage come from the official index report. Track aggregation and coverage adjustment can therefore make Score differ from the index's raw value. iSarcasmEval uses its English track-A headline rather than a nonexistent combined summary score. All values below are generated from this v3 run, not the v2 card.
The model repository does not include prediction/result files. These belong in a
separate results Dataset under runs/lemondecider-v3-chunked-public03/; attach its
published link and immutable model revision when submitting. No Dataset URL is
invented here. Publication code has naming-only differences from the historical
service; its planning/prediction implementations are unchanged (release notes).
The current Dataset publication copy normalized response-model labels; preserve
original untouched predictions for review or obtain reviewer acceptance of that
transformation. A naming-cleanup rescore is not a new inference evaluation.
Install a hardware-compatible Torch 2.9.0 build in a separate Python 3.12
environment, then python -m pip install -r requirements.txt.
The requirements file is a candidate recipe, not a validated NVIDIA lockfile.
Clean NVIDIA compatibility has not been verified by this packaging operation.
Download the whole repository at an immutable published v3 revision; custom code
executes during loading, so inspect it first.
From this repository root:
HTTP endpoints: GET /health, GET /v1/models, POST /v1/systemone.
The service binds to localhost by default. Use LEMONDECIDER_API_KEY for optional
bearer authentication; the provided local smoke client assumes it is unset.
code/serve.sh accepts PORT, DEVICE, CHECKPOINT, PYTHON and
AIS_SERVER_CPU_THREADS. Never expose an unauthenticated service publicly.
A long question list is recursively bisected in its original order. Every chunk
retains the complete state and options. Planning finishes before any forward;
if even one singleton cannot fit, the whole request returns HTTP 422. Returned
answers keep their original IDs, and input usage sums all chunks including
repeated state. No reread, option pruning or benchmark-specific rendering is used.
The root model.py is retained for file-layout compatibility but uses the legacy
independent-question path; it is NOT the reproducing CLI for this joint v3 run.
LICENSE and LICENSE.code are preserved from the v3 export (Apache-2.0 and MIT
texts respectively). Retain all applicable upstream and author notices; this
packaging does not expand rights over training or evaluation data.
The Lemon project builds on the Qwen backbone and upstream typed-decision runtime work. Attribution and notices remain in the original source and license files.
import jsonimport sysfrom pathlib import Path
checkpoint = Path("./LemonDecider").resolve()sys.path.insert(0, str(checkpoint / "code"))from serve_312k import LemonDeciderHFService
service = LemonDeciderHFService(checkpoint, "cuda:0", None)request = { "state": "The customer wants to return a damaged package.", "questions": { "action": { "type": "choice", "instructions": "Choose the next action.", "criteria": {"refund": "Offer a refund", "tracking": "Check tracking"} }, "damaged": {"type": "noul", "instructions": "Is the package damaged?"} }}print(json.dumps(service.predict(request), indent=2))python code/verify_files.pypython tests/test_chunking.pyCUDA_VISIBLE_DEVICES=0 python code/infer.py --input examples/request.json# Alternatively, start the local HTTP service:CUDA_VISIBLE_DEVICES=0 bash code/serve.sh# In another terminal:python code/smoke_test.py