Instructions to use zai-org/GLM-OCR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/GLM-OCR with Transformers:

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

pipe = pipeline("image-text-to-text", model="zai-org/GLM-OCR")
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 AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("zai-org/GLM-OCR")
model = AutoModelForMultimodalLM.from_pretrained("zai-org/GLM-OCR", 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 = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
AMD Developer Cloud
Local Apps Settings

vLLM

How to use zai-org/GLM-OCR with vLLM:

Install from pip and serve model

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

SGLang

How to use zai-org/GLM-OCR 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 "zai-org/GLM-OCR" \
    --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": "zai-org/GLM-OCR",
		"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 "zai-org/GLM-OCR" \
        --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": "zai-org/GLM-OCR",
		"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 zai-org/GLM-OCR with Docker Model Runner:
```
docker model run hf.co/zai-org/GLM-OCR
```

staghado commited on Mar 5

Commit

0b03da6

verified ·

1 Parent(s): 0365ee8

Update .eval_results/olmocrbench.yaml

Browse files

Files changed (1) hide show

.eval_results/olmocrbench.yaml +9 -0

.eval_results/olmocrbench.yaml CHANGED Viewed

@@ -4,6 +4,7 @@
   value: 75.2
   notes: "Excluding Headers & Footers category. Using ZAI API."
   source:
     name: GLM-OCR API evaluation
     user: staghado
 - dataset:
@@ -11,6 +12,7 @@
     task_id: arxiv_math
   value: 80.7
   source:
     name: GLM-OCR API evaluation
     user: staghado
 - dataset:
@@ -18,6 +20,7 @@
     task_id: old_scans_math
   value: 68.3
   source:
     name: GLM-OCR API evaluation
     user: staghado
 - dataset:
@@ -25,6 +28,7 @@
     task_id: table_tests
   value: 77.6
   source:
     name: GLM-OCR API evaluation
     user: staghado
 - dataset:
@@ -32,6 +36,7 @@
     task_id: old_scans
   value: 37.6
   source:
     name: GLM-OCR API evaluation
     user: staghado
 - dataset:
@@ -39,6 +44,7 @@
     task_id: multi_column
   value: 76.7
   source:
     name: GLM-OCR API evaluation
     user: staghado
 - dataset:
@@ -46,6 +52,7 @@
     task_id: long_tiny_text
   value: 86.9
   source:
     name: GLM-OCR API evaluation
     user: staghado
 - dataset:
@@ -53,6 +60,7 @@
     task_id: headers_footers
   value: 95.8
   source:
     name: GLM-OCR API evaluation
     user: staghado
 - dataset:
@@ -60,5 +68,6 @@
     task_id: baseline
   value: 98.8
   source:
     name: GLM-OCR API evaluation
     user: staghado

   value: 75.2
   notes: "Excluding Headers & Footers category. Using ZAI API."
   source:
+    url: https://huggingface.co/zai-org/GLM-OCR
     name: GLM-OCR API evaluation
     user: staghado
 - dataset:
     task_id: arxiv_math
   value: 80.7
   source:
+    url: https://huggingface.co/zai-org/GLM-OCR
     name: GLM-OCR API evaluation
     user: staghado
 - dataset:
     task_id: old_scans_math
   value: 68.3
   source:
+    url: https://huggingface.co/zai-org/GLM-OCR
     name: GLM-OCR API evaluation
     user: staghado
 - dataset:
     task_id: table_tests
   value: 77.6
   source:
+    url: https://huggingface.co/zai-org/GLM-OCR
     name: GLM-OCR API evaluation
     user: staghado
 - dataset:
     task_id: old_scans
   value: 37.6
   source:
+    url: https://huggingface.co/zai-org/GLM-OCR
     name: GLM-OCR API evaluation
     user: staghado
 - dataset:
     task_id: multi_column
   value: 76.7
   source:
+    url: https://huggingface.co/zai-org/GLM-OCR
     name: GLM-OCR API evaluation
     user: staghado
 - dataset:
     task_id: long_tiny_text
   value: 86.9
   source:
+    url: https://huggingface.co/zai-org/GLM-OCR
     name: GLM-OCR API evaluation
     user: staghado
 - dataset:
     task_id: headers_footers
   value: 95.8
   source:
+    url: https://huggingface.co/zai-org/GLM-OCR
     name: GLM-OCR API evaluation
     user: staghado
 - dataset:
     task_id: baseline
   value: 98.8
   source:
+    url: https://huggingface.co/zai-org/GLM-OCR
     name: GLM-OCR API evaluation
     user: staghado