Repository Issue Activity (beta)

#382 `inference()` / `decode_batch()` crash with `KeyError` when a batch has per-text label sets of different *lengths* (`labels: List[List[str]]`)

#381 Return the hidden state vectors for the found spans (a new argument for `inference` API call)

#135 Onnx runtime error with input_shape_size == size was false

#375 Feature Request: Support `Dict[str, str]` for labels in `inference()` (label descriptions)

#378 `predict_entities` truncates silently -- expose truncation programmatically

#123 Unable to load model in offline mode

#218 Quantization of onnx models results in very poor performance

#216 Unable to load model

#150 cannot import name 'SAFETENSORS_SINGLE_FILE' from 'huggingface_hub.constants'

#159 transformers.Trainer `load_best_model_at_end` doesn't work

#205 gliner spacy import (gliner_spacy) broken

#212 Gliner finetuning fail on the notebook example

#214 Finetuning fails on the demo notebook

#188 RuntimeError: The input size 0, plus negative padding 0 and 0 resulted in a negative output size, which is invalid. Check dimension 1 of your input.

#184 Error while fine-tuning model using example from "examples/finetune.ipynb": `RuntimeError: shape '[8, 129, 12, 512]' is invalid for input of size 8306688`

#162 Error loading model from cache in docker container

#167 Load local model example gives config error

#182 The checkpoint you are trying to load has model type gliner but Transformers does not recognize this architecture.

#173 GLiNER.from_pretrained raises OSError: config.json file not found in Hugging Face model repository

#169 Fine-tuning example is broken

#177 Conversion to ONXX

#178 ONNX conversion error in latest gliner version 0.2.10

#213 Failed to test Gliner finetuned model

#221 Demo doesn't work

#237 Converting GLiNER with ModernBERT backbone to onnx error