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

Libraries

How to use datalab-to/surya-ocr-2-gguf with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("datalab-to/surya-ocr-2-gguf")
model = AutoModelForMultimodalLM.from_pretrained("datalab-to/surya-ocr-2-gguf", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use datalab-to/surya-ocr-2-gguf with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf datalab-to/surya-ocr-2-gguf
# Run inference directly in the terminal:
llama cli -hf datalab-to/surya-ocr-2-gguf

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf datalab-to/surya-ocr-2-gguf
# Run inference directly in the terminal:
llama cli -hf datalab-to/surya-ocr-2-gguf

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf datalab-to/surya-ocr-2-gguf
# Run inference directly in the terminal:
./llama-cli -hf datalab-to/surya-ocr-2-gguf

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf datalab-to/surya-ocr-2-gguf
# Run inference directly in the terminal:
./build/bin/llama-cli -hf datalab-to/surya-ocr-2-gguf

Use Docker

docker model run hf.co/datalab-to/surya-ocr-2-gguf

LM Studio
Jan

vLLM

How to use datalab-to/surya-ocr-2-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "datalab-to/surya-ocr-2-gguf"
# 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/surya-ocr-2-gguf",
		"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/surya-ocr-2-gguf

SGLang

How to use datalab-to/surya-ocr-2-gguf 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/surya-ocr-2-gguf" \
    --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/surya-ocr-2-gguf",
		"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/surya-ocr-2-gguf" \
        --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/surya-ocr-2-gguf",
		"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"
						}
					}
				]
			}
		]
	}'

Ollama
How to use datalab-to/surya-ocr-2-gguf with Ollama:
```
ollama run hf.co/datalab-to/surya-ocr-2-gguf
```
Unsloth Desktop
Docker Model Runner
How to use datalab-to/surya-ocr-2-gguf with Docker Model Runner:
```
docker model run hf.co/datalab-to/surya-ocr-2-gguf
```

Lemonade

How to use datalab-to/surya-ocr-2-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull datalab-to/surya-ocr-2-gguf

Run and chat with the model

lemonade run user.surya-ocr-2-gguf-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

vikp commited on May 17

Commit

f18ef82

verified ·

1 Parent(s): 0aea19c

Update throughput numbers (5090 conc-sweep + Mac single row)

Browse files

Files changed (1) hide show

README.md +13 -13

README.md CHANGED Viewed

@@ -109,27 +109,27 @@ table_predictions = table.predict_full([Image.open("page.png")]) # full <table>
 ## Throughput
-Full-page OCR, 96 DPI input (~3,000 output tokens/page average), measured client-side against a running inference server.
 ### RTX 5090 (vllm)
-`vllm/vllm-openai:v0.20.1`, single RTX 5090 (32 GB), client-side concurrency 128, prefix caching off.
-| Concurrency | Pages/s | Tokens/s | Peak power |
-|---:|---:|---:|---:|
-| 128 | **5.64** | **13,829** | ~478 W (80 % of 600 W TDP) |
-### Apple Silicon (llama.cpp / Metal)
-`llama-server` with Metal backend, one process per `--parallel` level.
-| `--parallel` | Pages/s | Tokens/s | p50 (ms) | p95 (ms) |
-|---:|---:|---:|---:|---:|
-|       4 | 0.217   |     222 |   18,122 |   19,676 |
-|   **8** | **0.269** | **270** |   27,549 |   42,730 |
-|      16 | 0.264   |     286 |   53,166 |   70,378 |
-Knees at `--parallel=8` — Metal is decode-saturated past that point.
 ## Commercial Usage

 ## Throughput
+Full-page OCR, 96 DPI input (~2,400 output tokens/page average), measured client-side against a running inference server.
 ### RTX 5090 (vllm)
+`vllm/vllm-openai:v0.20.1`, single RTX 5090 (32 GB). Sustained power ~478 W (80% of 600 W TDP) across all concurrencies.
+| Concurrency | Pages/s | Tokens/s | p50 (ms) | p95 (ms) | avg tok/page |
+|---:|---:|---:|---:|---:|---:|
+|      32 |     3.67 |     8,870 |  6,744 | 21,741 | 2,420 |
+|      64 |     4.67 |    11,280 | 10,741 | 34,639 | 2,414 |
+| **128** | **5.35** | **12,884** | 18,915 | 42,538 | 2,410 |
+Throughput climbs from conc=32 → 128 but latency grows faster than capacity. Pick conc=64 for the latency/throughput knee, conc=128 for max throughput.
+### Apple Silicon (llama.cpp / Metal)
+`llama-server` with Metal backend.
+| `--parallel` | Pages/s | Tokens/s | p50 (ms) | p95 (ms) | avg tok/page | Power |
+|---:|---:|---:|---:|---:|---:|---:|
+| **8** | **0.108** | **254** | 59,313 | 129,173 | 2,360 | ~30 W |
 ## Commercial Usage