Add link to code repository (#1)
Browse files- Add link to code repository (b9f0d985e4cb2b9f80c021099a2d2836c7d6d877)
Co-authored-by: Niels Rogge <nielsr@users.noreply.huggingface.co>
README.md
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
---
|
2 |
-
license: apache-2.0
|
3 |
-
library_name: transformers
|
4 |
base_model: OpenGVLab/InternVL2-4B
|
|
|
|
|
5 |
pipeline_tag: image-text-to-text
|
6 |
---
|
7 |
|
@@ -137,9 +137,15 @@ tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast
|
|
137 |
pixel_values = load_image('./web_dfacd48d-d2c2-492f-b94c-41e6a34ea99f.png', max_num=6).to(torch.bfloat16).cuda()
|
138 |
generation_config = dict(max_new_tokens=1024, do_sample=True)
|
139 |
|
140 |
-
question = "<image
|
|
|
|
|
|
|
|
|
|
|
141 |
response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True)
|
142 |
-
print(f'User: {question}
|
|
|
143 |
```
|
144 |
|
145 |
|
|
|
1 |
---
|
|
|
|
|
2 |
base_model: OpenGVLab/InternVL2-4B
|
3 |
+
library_name: transformers
|
4 |
+
license: apache-2.0
|
5 |
pipeline_tag: image-text-to-text
|
6 |
---
|
7 |
|
|
|
137 |
pixel_values = load_image('./web_dfacd48d-d2c2-492f-b94c-41e6a34ea99f.png', max_num=6).to(torch.bfloat16).cuda()
|
138 |
generation_config = dict(max_new_tokens=1024, do_sample=True)
|
139 |
|
140 |
+
question = "<image>
|
141 |
+
You are a GUI task expert, I will provide you with a high-level instruction, an action history, a screenshot with its corresponding accessibility tree.
|
142 |
+
High-level instruction: {high_level_instruction}
|
143 |
+
Action history: {action_history}
|
144 |
+
Accessibility tree: {a11y_tree}
|
145 |
+
Please generate the low-level thought and action for the next step."
|
146 |
response, history = model.chat(tokenizer, pixel_values, question, generation_config, history=None, return_history=True)
|
147 |
+
print(f'User: {question}
|
148 |
+
Assistant: {response}')
|
149 |
```
|
150 |
|
151 |
|