| Listed on OpenModelMap | duola15 | open | 0 | disc |
| Add MMMU-Pro evaluation result | SaylorTwift | open | 0 | disc |
| Fix typo | taekeunkang | open | 0 | disc |
| Add ScreenSpot-Pro evaluation result (Qwen2.5-VL-3B-Instruct) | merve | open | 0 | disc |
| REDME.md | Fradeck619 | open | 0 | disc |
| Showcase: Real-Time Invoice Parser using Qwen2.5-VL | Liviu16 | open | 0 | disc |
| Suppress Verbosity | jsob7 | open | 0 | disc |
| task1234 | shahdabdelrhman8 | draft | 0 | disc |
| Using the vision encoder only | klu30 | open | 0 | disc |
| Update README.md | jangbyeongheon | open | 0 | disc |
| 🚩 Report: Copyright infringement | novelaaaaaaaaa | closed | 0 | disc |
| 如何转成ONNX模型 | FishTheSky | open | 0 | disc |
| Update config.json | Bohr | open | 0 | disc |
| How to extract visual feature map? | InspiringWaves | closed | 0 | disc |
| Upload added_tokens.json | hyunseoki | closed | 0 | disc |
| Change to Apache 2.0 Licnse | ehartford | open | 0 | disc |
| License | ehartford | open | 0 | disc |
| 本地推理得到奇怪的回答 (使用 4090) | hflin0613 | open | 0 | disc |
| Update qwen-vl-version to 0.11 in model-card | nhop | open | 0 | disc |
| Update README.md | Veenuz | closed | 0 | disc |
| ValueError: Image features and image tokens do not match: tokens: 27624, features 34828 | Jdemonn | open | 0 | disc |
| 模型加载报错 | ZqXu | open | 0 | disc |
| transformers 版本不支持该架构 | furontan | open | 0 | disc |
| System prompt | ksooklall | open | 0 | disc |
| Chat template of AutoTokenizer does not work on assistant mask tokens | doruktarhan6 | open | 0 | disc |
| How to change the temperature of output generation?? | IronmanSnap | open | 0 | disc |
| Update README.md | hemantho | open | 0 | disc |
| Remove self referencing base model | davanstrien | merged | 0 | disc |
| Distributed reasoning | Lucaslym | open | 0 | disc |
| Cannot use this model as Conversational agent in smolagent framework | IronmanSnap | open | 0 | disc |
| Cannot scale inference endpoint to zero MANUALLY | ArunSharma93 | open | 0 | disc |
| How much VRAM is required? I have 8gb RTX 3060 and seems in sufficient | LawItApps | open | 0 | disc |
| tokenizer size | dsanddkjad | open | 0 | disc |
| Fix model tree—Current loops back to itself, new loops to Qwen2.5-3B-Instruct | deleted | open | 0 | disc |
| Add project page, Github repo and paper | nielsr | open | 0 | disc |
| RTX 4090 cant process videos above 4 mins | IronmanSnap | open | 0 | disc |
| Issue: cannot import name 'Qwen2_5_VLForConditionalGeneration' from 'transformers'. Anyone found why this issue persists and any solution to it? | IronmanSnap | closed | 0 | disc |
| Update preprocessor_config.json | Isotr0py | open | 0 | disc |
| Dimension out of range (expected to be in range of [-3, 2], but got 3) | oshyshko | open | 0 | disc |
| Licensing of Qwen2.5-VL | goodev | open | 0 | disc |
| Vision tokens missing from chat template | depasquale | open | 0 | disc |
| Update README.md | manu | open | 0 | disc |
| License? | smdesai | closed | 0 | disc |
| How to add this model to ollama | hellostevehaha | open | 0 | disc |
| Rename README.md to какая инвестиция перспективна 2025 | ProtasBali | open | 0 | disc |
| Memory requirements | sskorol | open | 0 | disc |
| Deploying on inference endpoint not working | crbo | open | 0 | disc |
| Quantized Qwen2.5-VL models | fortminors | open | 0 | disc |
| Update README.md | KatyTheCutie | open | 0 | disc |
| Remove recursive base_model | davanstrien | open | 0 | disc |
| A minor typo of the score on AndroidWorld | BoyuNLP | open | 0 | disc |