Update chat_template.json

REPLACE

    "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"

TO

    "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"

README.md

@@ -6,16 +6,14 @@ tags:
 base_model:
 - Qwen/Qwen2-VL-2B-Instruct
 license: mit
-tasks:
-  - image-text-to-text
 ---
-[Github](https://github.com/showlab/ShowUI/tree/main) | [arXiv](https://arxiv.org/abs/2411.17465) | [HF Paper](https://huggingface.co/papers/2411.17465) | [Studio](https://www.modelscope.cn/studios/AI-ModelScope/ShowUI) | [Datasets](https://huggingface.co/datasets/showlab/ShowUI-desktop-8K) | [Quick Start](https://www.modelscope.cn/models/AI-ModelScope/ShowUI-2B) 
+[Github](https://github.com/showlab/ShowUI/tree/main) | [arXiv](https://arxiv.org/abs/2411.17465) | [HF Paper](https://huggingface.co/papers/2411.17465) | [Spaces](https://huggingface.co/spaces/showlab/ShowUI) | [Datasets](https://huggingface.co/datasets/showlab/ShowUI-desktop-8K) | [Quick Start](https://huggingface.co/showlab/ShowUI-2B) 
 <img src="examples/showui.jpg" alt="ShowUI" width="640">
 
 ShowUI is a lightweight (2B) vision-language-action model designed for GUI agents.
 
-##  Try our ModelScope Studio Demo
-https://www.modelscope.cn/studios/AI-ModelScope/ShowUI
+## 🤗 Try our HF Space Demo
+https://huggingface.co/spaces/showlab/ShowUI
 
 
 ## ⭐ Quick Start
@@ -49,7 +47,7 @@ model = Qwen2VLForConditionalGeneration.from_pretrained(
 min_pixels = 256*28*28
 max_pixels = 1344*28*28
 
-processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-2B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels)
+processor = AutoProcessor.from_pretrained("showlab/ShowUI-2B", min_pixels=min_pixels, max_pixels=max_pixels)
 ```
 
 2. **UI Grounding**
@@ -146,7 +144,7 @@ action_map = {
 ```python
 img_url = 'examples/chrome.png'
 split='web'
-system_prompt = _NAV_SYSTEM.format(_APP=split, _ACTION_SPACE=action_map[split])
+system_prompt = _NAV_SYSTEM.format(_APP=split, _ACTION_SPACE=action_map[split]) + _NAV_FORMAT
 query = "Search the weather for the New York city."
 
 messages = [