Laya vs GLiClass

Laya

Apache-2.0 code and weights, installed with pip install laya, with Python 3.10 to 3.13 tested in CI. Base checkpoints score 0.362 and 0.352 on the maintainers' typed-decisions benchmark against a 0.318 random baseline, so it needs fine-tuning.

GLiClass

An Apache-2.0 classifier that scores a whole label set in one encoder pass on the owner's hardware, with single-label, multi-label, hierarchical and few-shot modes. It returns label scores with no calibration claim, the bundled server has no authentication, and the last three test runs on the main branch, on 24 September 2026, failed.

Laya

1. Set LAYA_API_KEY before starting laya-serve. It listens on every interface by default
2. Gate on answer_confidence, not confidence, which measures entropy and doesn't match Jev's field
3. Shortlist choice questions with more than about 20 options using predict_shortlist or the laya_shortlist tool
4. Use semantic or opaque labels such as A and B, not yes and no, in choice questions. The checkpoints can follow the label text
5. Pass model="multilingual" and max_len=8192 for long documents. The English checkpoint stops at 512 tokens

GLiClass

1. Pass --host 127.0.0.1 to python -m gliclass.serve, or put the port behind your own gateway. The server checks no credential
2. On a machine without a GPU add --device cpu --dtype float32 --num-gpus-per-replica 0. The default configuration expects CUDA
3. Send one text a request to POST /gliclass. An array in texts is cut to its first item without an error
4. Set multi_label to false for one label from a set. The default scores each label independently, so scores do not sum to 1
5. Keep text plus labels under the pipeline's 1,024-token max_length, or use ZeroShotClassificationWithChunkingPipeline. Longer input is truncated silently