Update pipeline example
Browse files
README.md
CHANGED
@@ -9,7 +9,6 @@ tags:
|
|
9 |
datasets:
|
10 |
- lmms-lab/LLaVA-OneVision-Data
|
11 |
pipeline_tag: image-text-to-text
|
12 |
-
inference: false
|
13 |
arxiv: 2408.03326
|
14 |
---
|
15 |
# LLaVA-Onevision Model Card
|
@@ -55,33 +54,22 @@ The model supports multi-image and multi-prompt generation. Meaning that you can
|
|
55 |
Below we used [`"llava-hf/llava-onevision-qwen2-0.5b-si-hf"`](https://huggingface.co/llava-hf/llava-onevision-qwen2-0.5b-si-hf) checkpoint.
|
56 |
|
57 |
```python
|
58 |
-
from transformers import pipeline
|
59 |
-
from PIL import Image
|
60 |
-
import requests
|
61 |
|
62 |
-
|
63 |
-
|
64 |
-
processor = AutoProcessor.from_pretrained(model_id)
|
65 |
-
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/ai2d-demo.jpg"
|
66 |
-
image = Image.open(requests.get(url, stream=True).raw)
|
67 |
-
|
68 |
-
# Define a chat history and use `apply_chat_template` to get correctly formatted prompt
|
69 |
-
# Each value in "content" has to be a list of dicts with types ("text", "image")
|
70 |
-
conversation = [
|
71 |
{
|
72 |
-
|
73 |
"role": "user",
|
74 |
"content": [
|
|
|
75 |
{"type": "text", "text": "What does the label 15 represent? (1) lava (2) core (3) tunnel (4) ash cloud"},
|
76 |
-
{"type": "image"},
|
77 |
],
|
78 |
},
|
79 |
]
|
80 |
-
prompt = processor.apply_chat_template(conversation, add_generation_prompt=True)
|
81 |
|
82 |
-
|
83 |
-
print(
|
84 |
-
>>> {
|
85 |
```
|
86 |
|
87 |
### Using pure `transformers`:
|
|
|
9 |
datasets:
|
10 |
- lmms-lab/LLaVA-OneVision-Data
|
11 |
pipeline_tag: image-text-to-text
|
|
|
12 |
arxiv: 2408.03326
|
13 |
---
|
14 |
# LLaVA-Onevision Model Card
|
|
|
54 |
Below we used [`"llava-hf/llava-onevision-qwen2-0.5b-si-hf"`](https://huggingface.co/llava-hf/llava-onevision-qwen2-0.5b-si-hf) checkpoint.
|
55 |
|
56 |
```python
|
57 |
+
from transformers import pipeline
|
|
|
|
|
58 |
|
59 |
+
pipe = pipeline("image-text-to-text", model="llava-onevision-qwen2-0.5b-si-hf")
|
60 |
+
messages = [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
61 |
{
|
|
|
62 |
"role": "user",
|
63 |
"content": [
|
64 |
+
{"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/ai2d-demo.jpg"},
|
65 |
{"type": "text", "text": "What does the label 15 represent? (1) lava (2) core (3) tunnel (4) ash cloud"},
|
|
|
66 |
],
|
67 |
},
|
68 |
]
|
|
|
69 |
|
70 |
+
out = pipe(text=messages, max_new_tokens=20)
|
71 |
+
print(out)
|
72 |
+
>>> [{'input_text': [{'role': 'user', 'content': [{'type': 'image', 'url': 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/ai2d-demo.jpg'}, {'type': 'text', 'text': 'What does the label 15 represent? (1) lava (2) core (3) tunnel (4) ash cloud'}]}], 'generated_text': 'Lava'}]
|
73 |
```
|
74 |
|
75 |
### Using pure `transformers`:
|