Qwen
/

Qwen2.5-VL-7B-Instruct

@@ -1,12 +1,11 @@
 ---
-license: apache-2.0
 language:
 - en
 pipeline_tag: image-text-to-text
 tags:
 - multimodal
-library_name: transformers
 ---
 # Qwen2.5-VL-7B-Instruct
@@ -16,6 +15,8 @@ library_name: transformers
 ## Introduction
 In the past five months since Qwen2-VL’s release, numerous developers have built new models on the Qwen2-VL vision-language models, providing us with valuable feedback. During this period, we focused on building more useful vision-language models. Today, we are excited to introduce the latest addition to the Qwen family: Qwen2.5-VL.
 #### Key Enhancements:
@@ -127,7 +128,7 @@ KeyError: 'qwen2_5_vl'
 We offer a toolkit to help you handle various types of visual input more conveniently, as if you were using an API. This includes base64, URLs, and interleaved images and videos. You can install it using the following command:
 ```bash
-# It's highly recommanded to use `[decord]` feature for faster video loading.
 pip install qwen-vl-utils[decord]==0.0.8
 ```
@@ -138,7 +139,7 @@ If you are not using Linux, you might not be able to install `decord` from PyPI.
 Here we show a code snippet to show you how to use the chat model with `transformers` and `qwen_vl_utils`:
 ```python
-from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
 from qwen_vl_utils import process_vision_info
 # default: Load the model on the available device(s)
@@ -384,7 +385,6 @@ print(output_texts)
 ### 🤖 ModelScope
 We strongly advise users especially those in mainland China to use ModelScope. `snapshot_download` can help you solve issues concerning downloading checkpoints.
 ### More Usage Tips
 For input images, we support local files, base64, and URLs. For videos, we currently only support local files.
@@ -525,4 +525,4 @@ If you find our work helpful, feel free to give us a cite.
   journal={arXiv preprint arXiv:2308.12966},
   year={2023}
 }
-```

 ---
 language:
 - en
+library_name: transformers
+license: apache-2.0
 pipeline_tag: image-text-to-text
 tags:
 - multimodal
 ---
 # Qwen2.5-VL-7B-Instruct
 ## Introduction
+This repository contains the model as described in [Qwen2.5-VL Technical Report](https://arxiv.org/abs/2502.13923).
 In the past five months since Qwen2-VL’s release, numerous developers have built new models on the Qwen2-VL vision-language models, providing us with valuable feedback. During this period, we focused on building more useful vision-language models. Today, we are excited to introduce the latest addition to the Qwen family: Qwen2.5-VL.
 #### Key Enhancements:
 We offer a toolkit to help you handle various types of visual input more conveniently, as if you were using an API. This includes base64, URLs, and interleaved images and videos. You can install it using the following command:
 ```bash
+# It's highly recommended to use `[decord]` feature for faster video loading.
 pip install qwen-vl-utils[decord]==0.0.8
 ```
 Here we show a code snippet to show you how to use the chat model with `transformers` and `qwen_vl_utils`:
 ```python
+from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
 from qwen_vl_utils import process_vision_info
 # default: Load the model on the available device(s)
 ### 🤖 ModelScope
 We strongly advise users especially those in mainland China to use ModelScope. `snapshot_download` can help you solve issues concerning downloading checkpoints.
 ### More Usage Tips
 For input images, we support local files, base64, and URLs. For videos, we currently only support local files.
   journal={arXiv preprint arXiv:2308.12966},
   year={2023}
 }
+```