Instructions to use HarborYuan/Sa2VA-LLaVA-1.5-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HarborYuan/Sa2VA-LLaVA-1.5-7B with Transformers:

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

pipe = pipeline("image-text-to-text", model="HarborYuan/Sa2VA-LLaVA-1.5-7B", 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("HarborYuan/Sa2VA-LLaVA-1.5-7B", trust_remote_code=True, dtype="auto")

sam2

How to use HarborYuan/Sa2VA-LLaVA-1.5-7B with sam2:

# Use SAM2 with images
import torch
from sam2.sam2_image_predictor import SAM2ImagePredictor

predictor = SAM2ImagePredictor.from_pretrained(HarborYuan/Sa2VA-LLaVA-1.5-7B)

with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16):
    predictor.set_image(<your_image>)
    masks, _, _ = predictor.predict(<input_prompts>)

# Use SAM2 with videos
import torch
from sam2.sam2_video_predictor import SAM2VideoPredictor

predictor = SAM2VideoPredictor.from_pretrained(HarborYuan/Sa2VA-LLaVA-1.5-7B)

with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16):
    state = predictor.init_state(<your_video>)

    # add new prompts and instantly get the output on the same frame
    frame_idx, object_ids, masks = predictor.add_new_points(state, <your_prompts>):

    # propagate the prompts to get masklets throughout the video
    for frame_idx, object_ids, masks in predictor.propagate_in_video(state):
        ...

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use HarborYuan/Sa2VA-LLaVA-1.5-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HarborYuan/Sa2VA-LLaVA-1.5-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HarborYuan/Sa2VA-LLaVA-1.5-7B",
		"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/HarborYuan/Sa2VA-LLaVA-1.5-7B

SGLang

How to use HarborYuan/Sa2VA-LLaVA-1.5-7B 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 "HarborYuan/Sa2VA-LLaVA-1.5-7B" \
    --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": "HarborYuan/Sa2VA-LLaVA-1.5-7B",
		"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 "HarborYuan/Sa2VA-LLaVA-1.5-7B" \
        --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": "HarborYuan/Sa2VA-LLaVA-1.5-7B",
		"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 HarborYuan/Sa2VA-LLaVA-1.5-7B with Docker Model Runner:
```
docker model run hf.co/HarborYuan/Sa2VA-LLaVA-1.5-7B
```

Sa2VA-LLaVA-1.5-7B

Sa2VA-LLaVA-1.5-7B is a Sa2VA model built on LLaVA-1.5-7B (CLIP-ViT-L-336 vision encoder + Vicuna-7B language model) with a SAM2 grounding encoder. The MLLM predicts a [SEG] token whose hidden state conditions the SAM2 mask decoder, producing dense image and video referring segmentation alongside open-ended chat. It is intended as a LISA-comparable baseline within the Sa2VA family.

This checkpoint is self-contained: the SAM2 grounding code is vendored into the repository, so it loads with trust_remote_code=True without any extra packages.

Results

Image referring segmentation (cIoU):

RefCOCO val / testA / testB	RefCOCO+ val / testA / testB	RefCOCOg val / test
80.3 / 82.4 / 76.7	73.1 / 78.0 / 66.2	79.2 / 80.1

Video referring segmentation (J&F):

MeViS (val_u)	ReVOS	Ref-DAVIS17
54.8	54.0	74.6

Grounded conversation generation (GCG, val):

AP50	mIoU	Recall
31.2	66.6	43.7

Usage

import torch
from transformers import AutoModel, AutoTokenizer
from PIL import Image

path = "HarborYuan/Sa2VA-LLaVA-1.5-7B"
model = AutoModel.from_pretrained(
    path, torch_dtype=torch.bfloat16, trust_remote_code=True, low_cpu_mem_usage=True,
).eval().cuda()
tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True)

image = Image.open("your_image.jpg").convert("RGB")
out = model.predict_forward(
    image=image,
    text="<image>Please segment the dog in the image.",
    tokenizer=tokenizer,
)
print(out["prediction"])          # text response containing [SEG]
masks = out["prediction_masks"]   # list of boolean masks at the original image size

Load in bfloat16 (the lm_head is kept in higher precision; torch_dtype="auto" mixes dtypes and fails). This model uses a tokenizer (not an AutoProcessor).

For video, pass video=[frame0, frame1, ...] (a list of PIL images) instead of image.

Notes

SAM2 grounding input resolution is 1024.
Built on Sa2VA.

Downloads last month: 24

Safetensors

Model size

7B params

Tensor type

F32