#1919th of 90 in Open models
gliner
Small zero-shot named entity recognition models with training and serving code
- Stars
- 4.3k
- License
- Apache-2.0
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- Python
3,084 on 25 Apr 20264,272 on 14 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
GLiNER is a Python framework for training and running small transformer models that extract entities of any user-supplied label from text, without task-specific training. Variants cover bi-encoder label scaling, joint entity and relation extraction, streaming NER and PII detection. It runs on CPU, supports FP16/INT8 quantization, torch.compile and ONNX export, and includes a Ray Serve HTTP server.
Who it is for: Engineers needing local entity extraction or PII redaction without an LLM
Strengths
- Arbitrary entity labels at inference time, no labeled data needed
- Runs on CPU; FP16, INT8, torch.compile and ONNX export available
- Several architectures: uni-encoder, bi-encoder, relation extraction, decoder, streaming
- Includes fine-tuning script and Ray Serve server with dynamic batching
Weaknesses
- Uni-encoder handles only about 50 entity types; more needs the bi-encoder
- INT8 accuracy requires models trained with quantization-aware training
- Classification, entity linking and schema extraction live in separate projects
- Serving layer depends on Ray Serve, an extra install
What it needs
- GPU optional
- Compose
- Needs PyTorch, Ray Serve (optional, for serving)
- Models: GLiNER uni-encoder, GLiNER bi-encoder, GLiNER RelEx, GLiNER Decoder, StreamingSpan
- port 8000
What changed
- v0.2.30 ↗ (opens in a new tab)Breaking
“FP8 inference requires torchao and a CUDA GPU with compute capability 8.9 or newer. Use compilation for the intended optimized execution path.”
- v0.2.29 ↗ (opens in a new tab)Breaking
“Install gliner[onnx] for CPU ONNX Runtime, gliner[gpu] for GPU ONNX Runtime, or gliner[openvino] for OpenVINO. Install the separate onnx package when exporting to ONNX.”
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Open models
See all 90| Rank | Project | Score |
|---|---|---|
| 1 | ruviewWiFi CSI sensing on ESP32 for presence, breathing, heart rate and pose | 94 out of 100 |
| 2 | layaSingle-pass multilingual classifier returning typed decisions with calibrated odds | 88 out of 100 |
| 3 | rf-detrReal-time transformer models for object detection, segmentation and keypoints | 82 out of 100 |
| #4 | timesfmPretrained time-series foundation model for zero-shot forecasting from Google Research | 80 out of 100 |
| #5 | open_clipPyTorch library for training and running CLIP-style image-text models | 79 out of 100 |