| IvanWong | lkwlvan | draft | 0 | disc |
| Add MDPBench private evaluation result | Delores-Lin | open | 0 | disc |
| Multilingual powerhouse — testing for mobile deployment | 3morixd | open | 0 | disc |
| Listed on OpenModelMap | duola15 | open | 0 | disc |
| Tag as image-to-text (revert https://huggingface.co/zai-org/GLM-OCR/discussions/57) | Wauplin | open | 0 | disc |
| Remove hardcode pipeline_tag (must be image-text-to-text) | Wauplin | merged | 0 | disc |
| ValueError: Task 'image-to-text' not supported for provider 'zai-org'. Available tasks: ['conversational', 'text-to-image'] | procioni | open | 0 | disc |
| Please support vietnamese | Duonglv | open | 0 | disc |
| OCR | dharm112 | draft | 0 | disc |
| Add ParseBench evaluation results | boyang-runllama | open | 0 | disc |
| Add ParseBench evaluation results | boyang-runllama | closed | 0 | disc |
| Add MDPBench evaluation results | Delores-Lin | merged | 0 | disc |
| Inconsistent results | TheMrguiller | open | 0 | disc |
| 'image-to-text' not supported for provider 'zai-org' | BelegNeurion | open | 0 | disc |
| instructions dont do anything is there way to actualy make it listen to it? | dimitarx | open | 0 | disc |
| Retail Flyer - Constant hallucination despite prompt injection. | bradomni | open | 0 | disc |
| What is the testing setup? | wamreyaz | open | 0 | disc |
| Why does the chat template include reasoning/thinking components? | usrlocalben | open | 0 | disc |
| add technical report | JaredforReal | merged | 0 | disc |
| Add OlmOCRBench evaluation results | staghado | merged | 0 | disc |
| Critical Hallucinations and Cross-Script Confusion in Multilingual Stress Test (CJK + Cyrillic) | The1Just | open | 0 | disc |
| Poor Russian language generation. | borisbek | closed | 0 | disc |
| Upload Covid Instructions.jpg | manikandannet | open | 0 | disc |
| Made a llama.cpp version | notune | closed | 0 | disc |
| Does model support bounding box outputs? | athrael-soju | closed | 0 | disc |
| Performance Issue (Transformers) | THEMi11 | closed | 0 | disc |
| Easy install without transformers | PartyParrot | open | 0 | disc |
| how to work with this model | longkyte | closed | 0 | disc |
| ERROR occurs when loading AutoProcessor | FronyAI | closed | 0 | disc |
| how to start with zero knowledge ? | JRYAN723 | open | 0 | disc |
| Readme | Toyosi22 | closed | 0 | disc |
| ggggg | bojesomo | closed | 0 | disc |
| this is good | n0tdapo | open | 0 | disc |
| Table regonition doesn't work well for multiple table | OumarDicko | open | 0 | disc |
| Images | BigRichMe | closed | 0 | disc |
| Please Add the ARABIC language also | ANASDAVOODTK | open | 0 | disc |
| Update README.md | JaredforReal | merged | 0 | disc |
| move SDK and add github reference | JaredforReal | closed | 0 | disc |
| move SDK | JaredforReal | closed | 0 | disc |
| MTP and trading | Maryann8106 | open | 0 | disc |
| Rename README.md to README.md yy | DannySc | closed | 0 | disc |
| lets prove it | Miggyjp | closed | 0 | disc |
| jkhjk | nameless98 | open | 0 | disc |
| Rename README.md to READing | Lyonblaze | open | 0 | disc |
| what do we really have to know | smarttech445 | open | 0 | disc |
| Update README.md | wisemansaids | open | 0 | disc |
| Inquery | melk525 | open | 0 | disc |
| Inquery | melk525 | open | 0 | disc |
| GLM-OCR very slow on Tesla T4 (~40s per image) even with GPU — is this expected? | 905saini | open | 0 | disc |
| Could this model extract text location or coordinate? | ExChaosen | open | 0 | disc |
| Training data details - sources and license | nramrakhiyani | open | 0 | disc |
| Requesting Example for Structured Information Extraction via cURL | andynoodles | open | 0 | disc |
| Ekpenta | WrldKING | closed | 0 | disc |
| No text output inferencing with ollama? | frankslin | open | 0 | disc |
| GLM-OCR: A Tiny 0.9B-Parameter Model That Punches Far Above Its Weight | Javedalam | open | 0 | disc |
| When will there be better support for vLLM? | Xiakj | open | 0 | disc |
| Working without the Sdk? | meganoob1337 | closed | 0 | disc |
| Thanks for using the PP-DocLayoutV3 model from PaddleOCR-VL-1.5 | ChengCui | closed | 0 | disc |
| Update README.md | JaredforReal | merged | 0 | disc |
| Update README.md | JaredforReal | closed | 0 | disc |
| Installation Video and Testing - Step by Step | fahdmirzac | open | 0 | disc |