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

71c2299

verified ·

1 Parent(s): 0587b30

Upload LlavaNextForConditionalGeneration

Browse files

Files changed (5) hide show

config.json +2 -2
generation_config.json +2 -2
model-00001-of-00003.safetensors +1 -1
model-00002-of-00003.safetensors +1 -1
model-00003-of-00003.safetensors +1 -1

config.json CHANGED Viewed

@@ -66,7 +66,7 @@
   "multimodal_projector_bias": true,
   "projector_hidden_act": "gelu",
   "text_config": {
-    "_name_or_path": "/gpfs/scratch/ehpc209/retrain_tmp/vlm_ckpts/finetune/towerp_2b_instruct/",
     "add_faster_video": false,
     "add_time_instruction": false,
     "architectures": [
@@ -161,7 +161,7 @@
     "mm_use_im_start_end": false,
     "mm_vision_select_feature": "patch",
     "mm_vision_select_layer": -2,
-    "mm_vision_tower": "/gpfs/scratch/ehpc209/hf_models/siglip2-so400m-patch14-384/",
     "mm_vision_tower_lr": 2e-06,
     "model_type": "gemma2",
     "num_attention_heads": 8,

   "multimodal_projector_bias": true,
   "projector_hidden_act": "gelu",
   "text_config": {
+    "_name_or_path": "/mnt/scratch-artemis/gviveiros/TowerVision/llava-next-native/towerp_2b_instruct/",
     "add_faster_video": false,
     "add_time_instruction": false,
     "architectures": [
     "mm_use_im_start_end": false,
     "mm_vision_select_feature": "patch",
     "mm_vision_select_layer": -2,
+    "mm_vision_tower": "/mnt/scratch-artemis/gviveiros/siglip2-so400m-patch14-384/",
     "mm_vision_tower_lr": 2e-06,
     "model_type": "gemma2",
     "num_attention_heads": 8,

generation_config.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 3,
   "cache_implementation": "hybrid",
-  "eos_token_id": 4,
   "pad_token_id": 0,
   "transformers_version": "4.52.0.dev0"
 }

 {
   "_from_model_config": true,
+  "bos_token_id": 2,
   "cache_implementation": "hybrid",
+  "eos_token_id": 107,
   "pad_token_id": 0,
   "transformers_version": "4.52.0.dev0"
 }

model-00001-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95b9527cc0f5870ecb44178fcd0590962a16b728c633bab97c8ff17c7b6227f0
 size 4973252496

 version https://git-lfs.github.com/spec/v1
+oid sha256:73b13aa27ee5bd1f3d488a6e0147759fb3c72eda406c0dd503ffbfa71e0eb41f
 size 4973252496

model-00002-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ce01202fe4f108f4016b6bc5a469fd1f6adb8b0bc7ab4bfbdc8703042ebf9e9
 size 4983446008

 version https://git-lfs.github.com/spec/v1
+oid sha256:83e78fbd1e1c4ca7a004fc08cf464947bc5ab04126b68b34a44580f8dfa5224e
 size 4983446008

model-00003-of-00003.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ce886d29cefb945e28706c1f3b4dc5fc954741353c5077e2de2133bd58b4f2b
 size 2123643328

 version https://git-lfs.github.com/spec/v1
+oid sha256:9be1dfbf34e2977863ca41794c9414d3979b34f876ed2c71990b336e77766e6a
 size 2123643328