Instructions to use smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI with Transformers:

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

pipe = pipeline("image-text-to-text", model="smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI")
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("smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI")
model = AutoModelForImageTextToText.from_pretrained("smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI")
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 smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI",
		"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/smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI

SGLang

How to use smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI 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 "smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI" \
    --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": "smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI",
		"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 "smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI" \
        --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": "smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI",
		"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 smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI with Docker Model Runner:
```
docker model run hf.co/smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI
```

amir.mahla@huggingface.co commited on Sep 18, 2025

Commit

32624be

1 Parent(s): e7129dd

PUSH last checkpoint

Browse files

Files changed (7) hide show

README.md +3 -6
all_results.json +11 -11
eval_results.json +5 -5
model.safetensors +1 -1
train_results.json +6 -6
trainer_state.json +0 -0
training_args.bin +2 -2

README.md CHANGED Viewed

@@ -1,18 +1,15 @@
 ---
 datasets: smolagents/aguvis-stage-2
 library_name: transformers
-model_name: SmolVLM2-2.2B-Instruct-Agentic-GUI
 tags:
 - generated_from_trainer
 - open-r1
 - vision-language
 - vlm
-- trl
-- sft
 licence: license
 ---
-# Model Card for SmolVLM2-2.2B-Instruct-Agentic-GUI
 This model is a fine-tuned version of [None](https://huggingface.co/None) on the [smolagents/aguvis-stage-2](https://huggingface.co/datasets/smolagents/aguvis-stage-2) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
@@ -23,14 +20,14 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 from transformers import pipeline
 question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="smolagents/SmolVLM2-2.2B-Instruct-Agentic-GUI", device="cuda")
 output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
 print(output["generated_text"])
 ```
 ## Training procedure
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/huggingface/smolagents/runs/fafnjj0e)
 This model was trained with SFT.

 ---
 datasets: smolagents/aguvis-stage-2
 library_name: transformers
 tags:
 - generated_from_trainer
 - open-r1
 - vision-language
 - vlm
 licence: license
 ---
+# Model Card for None
 This model is a fine-tuned version of [None](https://huggingface.co/None) on the [smolagents/aguvis-stage-2](https://huggingface.co/datasets/smolagents/aguvis-stage-2) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 from transformers import pipeline
 question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
 output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
 print(output["generated_text"])
 ```
 ## Training procedure
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/huggingface/smolagents/runs/9jig6y4c)
 This model was trained with SFT.

all_results.json CHANGED Viewed

@@ -1,13 +1,13 @@
 {
-    "eval_loss": 0.6482115983963013,
-    "eval_runtime": 149.9453,
-    "eval_samples": 3639,
-    "eval_samples_per_second": 24.269,
-    "eval_steps_per_second": 0.76,
-    "total_flos": 1.0314062938243072e+16,
-    "train_loss": 0.7184352108531378,
-    "train_runtime": 49977.4428,
-    "train_samples": 360255,
-    "train_samples_per_second": 14.417,
-    "train_steps_per_second": 0.028
 }

 {
+    "eval_loss": 0.4539664685726166,
+    "eval_runtime": 141.8302,
+    "eval_samples": 3638,
+    "eval_samples_per_second": 25.65,
+    "eval_steps_per_second": 0.804,
+    "total_flos": 9795365997903872.0,
+    "train_loss": 0.5166227378120477,
+    "train_runtime": 48333.5779,
+    "train_samples": 360073,
+    "train_samples_per_second": 14.899,
+    "train_steps_per_second": 0.029
 }

eval_results.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
-    "eval_loss": 0.6482115983963013,
-    "eval_runtime": 149.9453,
-    "eval_samples": 3639,
-    "eval_samples_per_second": 24.269,
-    "eval_steps_per_second": 0.76
 }

 {
+    "eval_loss": 0.4539664685726166,
+    "eval_runtime": 141.8302,
+    "eval_samples": 3638,
+    "eval_samples_per_second": 25.65,
+    "eval_steps_per_second": 0.804
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0cc2775f67a58f2f49f72ee3cda5e75dcec41726d4248ab1590904f3957bac8
 size 4493654912

 version https://git-lfs.github.com/spec/v1
+oid sha256:2f35a1d63b330152bc12ccb0685c77ca95a832992639eff97e5ec51473d249d5
 size 4493654912

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
-    "total_flos": 1.0314062938243072e+16,
-    "train_loss": 0.7184352108531378,
-    "train_runtime": 49977.4428,
-    "train_samples": 360255,
-    "train_samples_per_second": 14.417,
-    "train_steps_per_second": 0.028
 }

 {
+    "total_flos": 9795365997903872.0,
+    "train_loss": 0.5166227378120477,
+    "train_runtime": 48333.5779,
+    "train_samples": 360073,
+    "train_samples_per_second": 14.899,
+    "train_steps_per_second": 0.029
 }

trainer_state.json CHANGED Viewed

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

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8a6aaab234537ac22f6e654d93a1438177e55229767e5163fa09044f87b23b7
-size 7544

 version https://git-lfs.github.com/spec/v1
+oid sha256:11aab7e60c1e4b330194483ff537da7366acadb2c5dceb7c17da2174c696abd3
+size 7608