Instructions to use utter-project/TowerVision-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use utter-project/TowerVision-2B with Transformers:

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

pipe = pipeline("image-text-to-text", model="utter-project/TowerVision-2B")
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("utter-project/TowerVision-2B")
model = AutoModelForImageTextToText.from_pretrained("utter-project/TowerVision-2B")
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

vLLM

How to use utter-project/TowerVision-2B with vLLM:

Install from pip and serve model

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

SGLang

How to use utter-project/TowerVision-2B 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 "utter-project/TowerVision-2B" \
    --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": "utter-project/TowerVision-2B",
		"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 "utter-project/TowerVision-2B" \
        --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": "utter-project/TowerVision-2B",
		"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 utter-project/TowerVision-2B with Docker Model Runner:
```
docker model run hf.co/utter-project/TowerVision-2B
```

Guilherme Viveiros commited on Aug 19, 2025

Commit

7436d0e

verified ·

1 Parent(s): 71c2299

Upload processor

Browse files

Files changed (4) hide show

chat_template.jinja +4 -5
special_tokens_map.json +14 -2
tokenizer.json +2 -2
tokenizer_config.json +4 -20

chat_template.jinja CHANGED Viewed

@@ -1,5 +1,4 @@
-{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '
-' }}{% if message['content'] is string %}{{ message['content'] }}{% else %}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>
-' }}{% endfor %}{# Render all text next #}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] }}{% endfor %}{% endif %}{{ '<|im_end|>' + '
-' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
-' }}{% endif %}

+{{ bos_token }}{% for message in messages %}{% if message['role'] == 'assistant' %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}<start_of_turn>{{ role }}
+{{ message['content'] | trim }}<end_of_turn>
+{% endfor %}{% if add_generation_prompt %}<start_of_turn>model
+{% endif %}

special_tokens_map.json CHANGED Viewed

@@ -3,8 +3,20 @@
     "<start_of_turn>",
     "<end_of_turn>"
   ],
-  "bos_token": "<|im_start|>",
-  "eos_token": "<|im_end|>",
   "pad_token": {
     "content": "<unk>",
     "lstrip": false,

     "<start_of_turn>",
     "<end_of_turn>"
   ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<end_of_turn>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "pad_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8d0799ced231dd489d7946291b0ffc36aede4ec352cfb98c7ae1555f55874ab
-size 34362989

 version https://git-lfs.github.com/spec/v1
+oid sha256:c4b297c2611e679fa3ad2e8e77a7894870338ee92c2bbfbeff2d5b65496c47fd
+size 34363057

tokenizer_config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "add_bos_token": false,
   "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
@@ -2001,31 +2001,15 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "256001": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "256002": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "additional_special_tokens": [
     "<start_of_turn>",
     "<end_of_turn>"
   ],
-  "bos_token": "<|im_start|>",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
   "extra_special_tokens": {},
   "model_max_length": 8192,
   "pad_token": "<unk>",
@@ -2033,7 +2017,7 @@
   "processor_class": "LlavaNextProcessor",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
-  "tokenizer_class": "GemmaTokenizer",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }

 {
+  "add_bos_token": true,
   "add_eos_token": false,
   "added_tokens_decoder": {
     "0": {
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
   "additional_special_tokens": [
     "<start_of_turn>",
     "<end_of_turn>"
   ],
+  "bos_token": "<bos>",
   "clean_up_tokenization_spaces": false,
+  "eos_token": "<end_of_turn>",
   "extra_special_tokens": {},
   "model_max_length": 8192,
   "pad_token": "<unk>",
   "processor_class": "LlavaNextProcessor",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizerFast",
   "unk_token": "<unk>",
   "use_default_system_prompt": false
 }