Instructions to use ibm-granite/granite-docling-258M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ibm-granite/granite-docling-258M with Transformers:

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

pipe = pipeline("image-text-to-text", model="ibm-granite/granite-docling-258M")
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("ibm-granite/granite-docling-258M")
model = AutoModelForMultimodalLM.from_pretrained("ibm-granite/granite-docling-258M", 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 ibm-granite/granite-docling-258M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ibm-granite/granite-docling-258M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ibm-granite/granite-docling-258M",
		"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/ibm-granite/granite-docling-258M

SGLang

How to use ibm-granite/granite-docling-258M 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 "ibm-granite/granite-docling-258M" \
    --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": "ibm-granite/granite-docling-258M",
		"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 "ibm-granite/granite-docling-258M" \
        --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": "ibm-granite/granite-docling-258M",
		"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 ibm-granite/granite-docling-258M with Docker Model Runner:
```
docker model run hf.co/ibm-granite/granite-docling-258M
```

asnassar commited on Jul 11, 2025

Commit

6298576

verified ·

1 Parent(s): 341382d

v0.0.2 (#3)

Browse files

- v0.0.2 (ecba62ead2399d4df4d3f69a180419e09d2dbb67)

Files changed (6) hide show

config.json +3 -10
generation_config.json +2 -2
merges.txt +0 -0
model.safetensors +1 -1
tokenizer_config.json +3 -3
trainer_state.json +0 -0

config.json CHANGED Viewed

@@ -5,20 +5,14 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 100257,
-  "eos_token_id": 100257,
-  "freeze_lm_head": true,
-  "freeze_text_layers": true,
-  "freeze_text_module_exceptions": [],
-  "freeze_vision_layers": true,
-  "freeze_vision_module_exceptions": [],
   "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 576,
   "image_token_id": 100270,
   "initializer_range": 0.02,
   "intermediate_size": 1536,
-  "lm_head_path": "/data1/checkpoints/v06-granite165m/step_2000000_ckp/",
   "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "idefics3",
@@ -47,7 +41,7 @@
   "scale_factor": 4,
   "text_config": {
     "architectures": [
-      "VLlama3ForCausalLM"
     ],
     "attention_bias": false,
     "attention_dropout": 0.0,
@@ -68,7 +62,6 @@
     "rms_norm_eps": 1e-05,
     "rope_scaling": null,
     "rope_theta": 10000.0,
-    "tie_word_embeddings": true,
     "torch_dtype": "bfloat16",
     "use_cache": true,
     "vocab_size": 100480

   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
+  "bos_token_id": 100264,
+  "eos_token_id": 100338,
   "head_dim": 64,
   "hidden_act": "silu",
   "hidden_size": 576,
   "image_token_id": 100270,
   "initializer_range": 0.02,
   "intermediate_size": 1536,
   "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "idefics3",
   "scale_factor": 4,
   "text_config": {
     "architectures": [
+      "llama"
     ],
     "attention_bias": false,
     "attention_dropout": 0.0,
     "rms_norm_eps": 1e-05,
     "rope_scaling": null,
     "rope_theta": 10000.0,
     "torch_dtype": "bfloat16",
     "use_cache": true,
     "vocab_size": 100480

generation_config.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 100257,
-  "eos_token_id": 100257,
   "pad_token_id": 128002,
   "transformers_version": "4.53.0.dev0"
 }

 {
   "_from_model_config": true,
+  "bos_token_id": 100264,
+  "eos_token_id": 100338,
   "pad_token_id": 128002,
   "transformers_version": "4.53.0.dev0"
 }

merges.txt ADDED Viewed

The diff for this file is too large to render. See raw diff

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33e612f587edfeaa9f5e8c42b20e52c5a74fdb47a4ec2cc569d005c6b1d400b5
 size 630993616

 version https://git-lfs.github.com/spec/v1
+oid sha256:92d6fa41f9edcb5ef51f9ac1844edb11dfdaf403473351d1ddbee0e883e42f25
 size 630993616

tokenizer_config.json CHANGED Viewed

@@ -1064,12 +1064,12 @@
     "<image>",
     "<end_of_utterance>"
   ],
-  "bos_token": "<|end_of_text|>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|end_of_text|>",
   "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|pad|>",
   "padding_side": "left",
   "processor_class": "Idefics3Processor",

     "<image>",
     "<end_of_utterance>"
   ],
+  "bos_token": "<|start_of_role|>",
   "clean_up_tokenization_spaces": false,
+  "eos_token": "<|end_of_utterance|>",
   "errors": "replace",
   "extra_special_tokens": {},
+  "model_max_length": 8192,
   "pad_token": "<|pad|>",
   "padding_side": "left",
   "processor_class": "Idefics3Processor",

trainer_state.json DELETED Viewed

The diff for this file is too large to render. See raw diff