Instructions to use infly/Infinity-Parser2-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use infly/Infinity-Parser2-Flash with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="infly/Infinity-Parser2-Flash")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("infly/Infinity-Parser2-Flash")
model = AutoModelForImageTextToText.from_pretrained("infly/Infinity-Parser2-Flash")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use infly/Infinity-Parser2-Flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "infly/Infinity-Parser2-Flash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "infly/Infinity-Parser2-Flash",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/infly/Infinity-Parser2-Flash

SGLang

How to use infly/Infinity-Parser2-Flash with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "infly/Infinity-Parser2-Flash" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "infly/Infinity-Parser2-Flash",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "infly/Infinity-Parser2-Flash" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "infly/Infinity-Parser2-Flash",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use infly/Infinity-Parser2-Flash with Docker Model Runner:
```
docker model run hf.co/infly/Infinity-Parser2-Flash
```

zuminghuang commited on 24 days ago

Commit

d86adac

verified ·

1 Parent(s): 75ee19c

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -80,7 +80,7 @@ We are excited to release Infinity-Parser2, our latest flagship document underst
       <td>92.85</td>
     </tr>
     <tr>
-      <td colspan=7>Layout Analysis (mIoU)</td>
     </tr>
     <tr>
       <td>DocLayNet</td>
@@ -110,7 +110,7 @@ We are excited to release Infinity-Parser2, our latest flagship document underst
       <td>-</td>
     </tr>
     <tr>
-      <td colspan=7>Element Parsing</td>
     </tr>
     <tr>
       <td>OmniDocBench-v1.5-TextBlock</td>
@@ -140,7 +140,7 @@ We are excited to release Infinity-Parser2, our latest flagship document underst
       <td>96.4</td>
     </tr>
     <tr>
-      <td colspan=7>Chart Parsing</td>
     </tr>
     <tr>
       <td>Chart2Table</td>
@@ -161,7 +161,7 @@ We are excited to release Infinity-Parser2, our latest flagship document underst
       <td>-</td>
     </tr>
     <tr>
-      <td colspan=7>Chemical Formula Parsing</td>
     </tr>
     <tr>
       <td>CoSyn_Chemical</td>
@@ -173,7 +173,7 @@ We are excited to release Infinity-Parser2, our latest flagship document underst
       <td>-</td>
     </tr>
     <tr>
-      <td colspan=7>Document VQA</td>
     </tr>
     <tr>
       <td>DocVQA (val)</td>
@@ -194,7 +194,7 @@ We are excited to release Infinity-Parser2, our latest flagship document underst
       <td>85.24*</td>
     </tr>
     <tr>
-      <td colspan=7>General Multimodal Understanding</td>
     </tr>
     <tr>
       <td>AI2D</td>

       <td>92.85</td>
     </tr>
     <tr>
+      <td colspan=7><b>Layout Analysis (mIoU)</b></td>
     </tr>
     <tr>
       <td>DocLayNet</td>
       <td>-</td>
     </tr>
     <tr>
+      <td colspan=7><b>Element Parsing</b></td>
     </tr>
     <tr>
       <td>OmniDocBench-v1.5-TextBlock</td>
       <td>96.4</td>
     </tr>
     <tr>
+      <td colspan=7><b>Chart Parsing</b></td>
     </tr>
     <tr>
       <td>Chart2Table</td>
       <td>-</td>
     </tr>
     <tr>
+      <td colspan=7><b>Chemical Formula Parsing</b></td>
     </tr>
     <tr>
       <td>CoSyn_Chemical</td>
       <td>-</td>
     </tr>
     <tr>
+      <td colspan=7><b>Document VQA</b></td>
     </tr>
     <tr>
       <td>DocVQA (val)</td>
       <td>85.24*</td>
     </tr>
     <tr>
+      <td colspan=7><b>General Multimodal Understanding</b></td>
     </tr>
     <tr>
       <td>AI2D</td>