Instructions to use datalab-to/chandra-ocr-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use datalab-to/chandra-ocr-2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="datalab-to/chandra-ocr-2")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("datalab-to/chandra-ocr-2")
model = AutoModelForMultimodalLM.from_pretrained("datalab-to/chandra-ocr-2", device_map="auto")
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 datalab-to/chandra-ocr-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "datalab-to/chandra-ocr-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "datalab-to/chandra-ocr-2",
		"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/datalab-to/chandra-ocr-2

SGLang

How to use datalab-to/chandra-ocr-2 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 "datalab-to/chandra-ocr-2" \
    --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": "datalab-to/chandra-ocr-2",
		"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 "datalab-to/chandra-ocr-2" \
        --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": "datalab-to/chandra-ocr-2",
		"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 datalab-to/chandra-ocr-2 with Docker Model Runner:
```
docker model run hf.co/datalab-to/chandra-ocr-2
```

davanstrien HF Staff commited on Mar 18

Commit

4d0f6d7

verified ·

1 Parent(s): 0e8490d

Fix task_id indentation: nest under dataset per spec

Browse files

Files changed (1) hide show

.eval_results/olmocrbench.yaml +9 -9

.eval_results/olmocrbench.yaml CHANGED Viewed

@@ -1,6 +1,6 @@
 - dataset:
     id: allenai/olmOCR-bench
-  task_id: overall
   value: 85.9
   source:
     url: https://huggingface.co/datalab-to/chandra-ocr-2
@@ -9,7 +9,7 @@
 - dataset:
     id: allenai/olmOCR-bench
-  task_id: arxiv_math
   value: 90.2
   source:
     url: https://huggingface.co/datalab-to/chandra-ocr-2
@@ -18,7 +18,7 @@
 - dataset:
     id: allenai/olmOCR-bench
-  task_id: old_scans_math
   value: 89.3
   source:
     url: https://huggingface.co/datalab-to/chandra-ocr-2
@@ -27,7 +27,7 @@
 - dataset:
     id: allenai/olmOCR-bench
-  task_id: table_tests
   value: 89.9
   source:
     url: https://huggingface.co/datalab-to/chandra-ocr-2
@@ -36,7 +36,7 @@
 - dataset:
     id: allenai/olmOCR-bench
-  task_id: old_scans
   value: 49.8
   source:
     url: https://huggingface.co/datalab-to/chandra-ocr-2
@@ -45,7 +45,7 @@
 - dataset:
     id: allenai/olmOCR-bench
-  task_id: headers_footers
   value: 92.5
   source:
     url: https://huggingface.co/datalab-to/chandra-ocr-2
@@ -54,7 +54,7 @@
 - dataset:
     id: allenai/olmOCR-bench
-  task_id: multi_column
   value: 83.5
   source:
     url: https://huggingface.co/datalab-to/chandra-ocr-2
@@ -63,7 +63,7 @@
 - dataset:
     id: allenai/olmOCR-bench
-  task_id: long_tiny_text
   value: 92.1
   source:
     url: https://huggingface.co/datalab-to/chandra-ocr-2
@@ -72,7 +72,7 @@
 - dataset:
     id: allenai/olmOCR-bench
-  task_id: baseline
   value: 99.6
   source:
     url: https://huggingface.co/datalab-to/chandra-ocr-2

 - dataset:
     id: allenai/olmOCR-bench
+    task_id: overall
   value: 85.9
   source:
     url: https://huggingface.co/datalab-to/chandra-ocr-2
 - dataset:
     id: allenai/olmOCR-bench
+    task_id: arxiv_math
   value: 90.2
   source:
     url: https://huggingface.co/datalab-to/chandra-ocr-2
 - dataset:
     id: allenai/olmOCR-bench
+    task_id: old_scans_math
   value: 89.3
   source:
     url: https://huggingface.co/datalab-to/chandra-ocr-2
 - dataset:
     id: allenai/olmOCR-bench
+    task_id: table_tests
   value: 89.9
   source:
     url: https://huggingface.co/datalab-to/chandra-ocr-2
 - dataset:
     id: allenai/olmOCR-bench
+    task_id: old_scans
   value: 49.8
   source:
     url: https://huggingface.co/datalab-to/chandra-ocr-2
 - dataset:
     id: allenai/olmOCR-bench
+    task_id: headers_footers
   value: 92.5
   source:
     url: https://huggingface.co/datalab-to/chandra-ocr-2
 - dataset:
     id: allenai/olmOCR-bench
+    task_id: multi_column
   value: 83.5
   source:
     url: https://huggingface.co/datalab-to/chandra-ocr-2
 - dataset:
     id: allenai/olmOCR-bench
+    task_id: long_tiny_text
   value: 92.1
   source:
     url: https://huggingface.co/datalab-to/chandra-ocr-2
 - dataset:
     id: allenai/olmOCR-bench
+    task_id: baseline
   value: 99.6
   source:
     url: https://huggingface.co/datalab-to/chandra-ocr-2