Instructions to use ByteDance/Sa2VA-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ByteDance/Sa2VA-4B with Transformers:

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

pipe = pipeline("image-text-to-text", model="ByteDance/Sa2VA-4B", trust_remote_code=True)
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 AutoModel
model = AutoModel.from_pretrained("ByteDance/Sa2VA-4B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ByteDance/Sa2VA-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ByteDance/Sa2VA-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ByteDance/Sa2VA-4B",
		"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/ByteDance/Sa2VA-4B

SGLang

How to use ByteDance/Sa2VA-4B 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 "ByteDance/Sa2VA-4B" \
    --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": "ByteDance/Sa2VA-4B",
		"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 "ByteDance/Sa2VA-4B" \
        --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": "ByteDance/Sa2VA-4B",
		"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 ByteDance/Sa2VA-4B with Docker Model Runner:
```
docker model run hf.co/ByteDance/Sa2VA-4B
```

Issue when running inference with the 4B model

by armandal - opened Jan 13, 2025

Discussion

armandal

Jan 13, 2025

Hi,
Thanks a lot for sharing the model,
I'm trying to make it work from the Quick start code shared on the HF page, but I'm facing an issue. Here is the error I get:

/usr/local/lib/python3.10/dist-packages/transformers/generation/utils.py in _sample(self, input_ids, logits_processor, stopping_criteria, generation_config, synced_gpus, streamer, **model_kwargs)
   3249 
   3250             if is_prefill:
-> 3251                 outputs = self(**model_inputs, return_dict=True)
   3252                 is_prefill = False
   3253             else:

TypeError: Qwen2ForCausalLM(
  (model): Qwen2Model(
    (embed_tokens): Embedding(151679, 2048)
    (layers): ModuleList(
      (0-35): 36 x Qwen2DecoderLayer(
        (self_attn): Qwen2FlashAttention2(
          (q_proj): Linear(in_features=2048, out_features=2048, bias=True)
          (k_proj): Linear(in_features=2048, out_features=256, bias=True)
          (v_proj): Linear(in_features=2048, out_features=256, bias=True)
          (o_proj): Linear(in_features=2048, out_features=2048, bias=False)
          (rotary_emb): Qwen2RotaryEmbedding()
        )
        (mlp): Qwen2MLP(
          (gate_proj): Linear(in_features=2048, out_features=11008, bias=False)
          (up_proj): Linear(in_features=2048, out_features=11008, bias=False)
          (down_proj): Linear(in_features=11008, out_features=2048, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): Qwen2RMSNorm((2048,), eps=1e-06)
        (post_attention_layernorm): Qwen2RMSNorm((2048,), eps=1e-06)
      )
    )
    (norm): Qwen2RMSNorm((2048,), eps=1e-06)
    (rotary_emb): Qwen2RotaryEmbedding()
  )
  (lm_head): Linear(in_features=2048, out_features=151679, bias=False)
) got multiple values for keyword argument 'return_dict'

It seems there is a problem with Qwen.

I work on colab enterprise with 2 A100 GPUs.

Any idea that could help to solve the problem ?

Thanks in advance

tbomez

Jan 13, 2025

I get ImportError: cannot import name 'Qwen2Config' from 'transformers', did you have any issues with this?

armandal

Jan 13, 2025

I get ImportError: cannot import name 'Qwen2Config' from 'transformers', did you have any issues with this?

armandal changed discussion status to closed Jan 13, 2025

armandal changed discussion status to open Jan 13, 2025

HarborYuan

Jan 14, 2025

Hi @tbomez @armandal ,

Thanks for your interest in our work. Please refer https://github.com/magic-research/Sa2VA/blob/main/requirements.txt for the dependency versions. The transformers lib changes rapidly, so please make the version exactly the same.

Xiangtai changed discussion status to closed Mar 13, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment