| erp2 | newapi980 | draft | 0 | disc |
| Delete model-00001-of-00005.safetensors | kiel2 | open | 0 | disc |
| Multilingual powerhouse — testing for mobile deployment | 3morixd | open | 0 | disc |
| Listed on OpenModelMap | duola15 | open | 0 | disc |
| Add MMMU-Pro evaluation result | SaylorTwift | open | 0 | disc |
| Qwen2.57Binit | miaohuairui | draft | 0 | disc |
| 科研需求 | zjutEvan | draft | 0 | disc |
| Add ScreenSpot-Pro evaluation result (Qwen2.5-VL-7B-Instruct) | merve | open | 0 | disc |
| Add missing Apache-2.0 license (aligned with other Qwen model repos) | angel-al | open | 0 | disc |
| Report Model not working via Hugging Face Router (50001 Internal Error) | Mustafahmdan | open | 0 | disc |
| The model suddenly is not working | Mustafahmdan | open | 0 | disc |
| Token Count Calculation in SFT Data Distribution Curation | tcy006 | open | 0 | disc |
| Transformers Version Error | thyjeff | open | 0 | disc |
| Create app.py | aabdullh100 | closed | 0 | disc |
| Optimal image format and size | yiftachd | open | 0 | disc |
| weien2 | weien2538 | draft | 0 | disc |
| Why tie_word_embeddings is False for 7B model? | pengzhenghao97 | open | 0 | disc |
| RTX 4090 with 24 GB VRAM train qwen2.5 7b using LLaMA Factory out of memory | islandzys | closed | 0 | disc |
| Update README.md | stevezkw | open | 0 | disc |
| Fix Video Inference - TypeError: process_vision_info() got an unexpected keyword argument 'return_video_kwargs' | developer0hye | open | 0 | disc |
| Batch inference gives addCriterion | clyao-123 | open | 0 | disc |
| Output logits differ significantly for differenet attn_implementations on image inputs | peefcat | open | 0 | disc |
| Confusion with the parameter fixed in visual ViT merger in source code. | Bytes-Lin | open | 0 | disc |
| Update README.md | xiaowei4ai | open | 0 | disc |
| In-context learning | Gilad-Deutch | open | 0 | disc |
| "ValueError: Image features and image tokens do not match: tokens: 0, features 2852" | jdkruzr | open | 0 | disc |
| Context Length | Fujiao | open | 0 | disc |
| run error | yangtao1 | open | 0 | disc |
| Model cannot be downloaded | sadabshiper | open | 0 | disc |
| Model Loading Issue: Some weights of the model checkpoint at Qwen/Qwen2.5-VL-7B-Instruct were not used when initializing Qwen2_5_VLForConditionalGeneration: | AmazingK2k3 | closed | 0 | disc |
| support function calling? | tasia | open | 0 | disc |
| Video Inference --> RuntimeError: torch.cat(): expected a non-empty list of Tensors | caput | open | 0 | disc |
| Inference on Tesla P40*2 or RTX 2080Ti *2, after fixing a bug(?) | luweigen | open | 0 | disc |
| CUDA out of memory for video understanding | luweigen | closed | 0 | disc |
| Update README.md | hemantho | open | 0 | disc |
| Chat template does not work | tonydavis629 | open | 0 | disc |
| Poor performance with simple table extraction task | hanshupe | open | 0 | disc |
| Base model for Qwen2.5-VL-7B-Instruct | zzlynxSG | open | 0 | disc |
| Request: DOI | mojan3 | open | 0 | disc |
| Best image resolution to OCR documents. | pashkash | closed | 0 | disc |
| Update README.md | 1h2b | closed | 0 | disc |
| pixel_values to RGB image | ococq | open | 0 | disc |
| Update README.md | teowu | open | 0 | disc |
| Qwen2.5-VL-7B-Instruct License? | radames | open | 0 | disc |
| Add link to paper page | nielsr | open | 0 | disc |
| For now, use this version of Transformers for vLLM. | mkvn | open | 0 | disc |
| Fine-tuning for Image Captioning and Image QA with Segmented Images | badhon1512 | open | 0 | disc |
| Model architectures ['Qwen2_5_VLForConditionalGeneration'] are not supported for now. | liujh123 | open | 0 | disc |
| No module named 'transformers.models.qwen2_5_vl.image_processing_qwen2_5_vl' | risonlovesakura | open | 0 | disc |
| XXX | mpasternak | open | 0 | disc |
| Update preprocessor_config.json | Isotr0py | merged | 0 | disc |
| finetune | andrewdeeplearning | open | 0 | disc |
| CUDA out of memory | goodzhangyu1999 | closed | 0 | disc |
| [Error] (Qwen2.5-VL-instruct-7B) Qwen2TokenizerFast object has no attribute 'tokenizer' | yus002 | open | 0 | disc |
| Vision tokens missing from chat template | depasquale | open | 0 | disc |
| Batch Inference会报错 | dingguofeng | open | 0 | disc |
| Hardware and vram requiremnt to run this model? | IronmanSnap | open | 0 | disc |
| Import error of ImportError of 'Qwen2_5_VLForConditionalGeneration' from transformers library | akbarmq01 | closed | 0 | disc |
| Request: DOI | arashinokage | open | 0 | disc |
| Can we use tools with this model? | barleyspectacular | open | 0 | disc |
| Qwen2.5-VL-7B-Instruct | kody111 | closed | 0 | disc |
| Bounding boxes coordinates | ljoana | open | 0 | disc |
| What engine can I use to deploy this model? | jjovalle99 | open | 0 | disc |
| Finetuning scripts for Qwen2.5-VL (No llama-factory) | 2U1 | open | 0 | disc |
| How to output in a Structured format with pydantic model in transformers model? | Vishva007 | closed | 0 | disc |
| Merging "Qwen2.5-7B-Instruct" text adapter into "Qwen2.5-VL-7B-Instruct" model | rameshch | open | 0 | disc |
| Video Inference - TypeError: process_vision_info() got an unexpected keyword argument 'return_video_kwargs' | rameshch | open | 0 | disc |
| Base models? | dbasu | open | 0 | disc |
| Ollama support? | YarvixPA | open | 0 | disc |
| some scores for minicpm-o 2.6 are not quite correct | yuzaa | open | 0 | disc |
| Provided code snippet not working? | alexpong | open | 0 | disc |
| Why are the 14b~32b models ignored again? | win10 | open | 0 | disc |
| Exception: Could not find the transformer layer class to wrap in the model. | atishay-scribe | open | 0 | disc |
| remove base_model | victor | merged | 0 | disc |