Instructions to use Eku127/swiftvln-habitat-3b-1ep-f32s4-overlap0-pf-h8-pool-s2-noembed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Eku127/swiftvln-habitat-3b-1ep-f32s4-overlap0-pf-h8-pool-s2-noembed with Transformers:

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

pipe = pipeline("image-text-to-text", model="Eku127/swiftvln-habitat-3b-1ep-f32s4-overlap0-pf-h8-pool-s2-noembed")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Eku127/swiftvln-habitat-3b-1ep-f32s4-overlap0-pf-h8-pool-s2-noembed")
model = AutoModelForMultimodalLM.from_pretrained("Eku127/swiftvln-habitat-3b-1ep-f32s4-overlap0-pf-h8-pool-s2-noembed", device_map="auto")
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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Eku127/swiftvln-habitat-3b-1ep-f32s4-overlap0-pf-h8-pool-s2-noembed with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Eku127/swiftvln-habitat-3b-1ep-f32s4-overlap0-pf-h8-pool-s2-noembed"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Eku127/swiftvln-habitat-3b-1ep-f32s4-overlap0-pf-h8-pool-s2-noembed",
		"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/Eku127/swiftvln-habitat-3b-1ep-f32s4-overlap0-pf-h8-pool-s2-noembed

SGLang

How to use Eku127/swiftvln-habitat-3b-1ep-f32s4-overlap0-pf-h8-pool-s2-noembed 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 "Eku127/swiftvln-habitat-3b-1ep-f32s4-overlap0-pf-h8-pool-s2-noembed" \
    --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": "Eku127/swiftvln-habitat-3b-1ep-f32s4-overlap0-pf-h8-pool-s2-noembed",
		"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 "Eku127/swiftvln-habitat-3b-1ep-f32s4-overlap0-pf-h8-pool-s2-noembed" \
        --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": "Eku127/swiftvln-habitat-3b-1ep-f32s4-overlap0-pf-h8-pool-s2-noembed",
		"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 Eku127/swiftvln-habitat-3b-1ep-f32s4-overlap0-pf-h8-pool-s2-noembed with Docker Model Runner:
```
docker model run hf.co/Eku127/swiftvln-habitat-3b-1ep-f32s4-overlap0-pf-h8-pool-s2-noembed
```

SwiftVLN for Habitat — Qwen2.5-VL 3B

Related Repositories

SwiftVLN: training and evaluation code for this checkpoint.

This checkpoint is designed for SwiftVLN on Habitat indoor navigation tasks. It predicts short navigation-action sequences from an instruction, the current RGB window, and sampled visual memory.

Model

Starting checkpoint: Qwen/Qwen2.5-VL-3B-Instruct
Training data: R2R, RxR, and EnvDrop expert trajectories
Training: 1 epoch, full-parameter fine-tuning, learning rate 2e-5
Context: 32 RGB frames, up to 8 uniformly sampled history frames
Prediction horizon: 4 actions
Memory: per-frame average pooling with stride 2

Repository name

swiftvln-habitat: SwiftVLN trained and evaluated in Habitat
3b: Qwen2.5-VL 3B backbone
1ep: trained for one epoch
f32s4: uses a 32-frame window and predicts four actions
overlap0: uses non-overlapping training windows
pf-h8: uses per-frame memory with up to eight history frames
pool-s2: applies average pooling with stride 2
noembed: uses no embedding enhancement

Reference Results

Evaluated on the full Habitat R2R validation splits with eight GPUs.

Split	Episodes	NE	OS	SR	SPL
`val_seen`	778	4.77	65.30	54.88	51.04
`val_unseen`	1,839	6.17	47.91	42.41	39.05

Usage

Use this checkpoint with the SwiftVLN evaluation guide. Pass this directory through MODEL_PATH and keep the full repository name unchanged because SwiftVLN derives the evaluation configuration from it.

Downloads last month: 10

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for Eku127/swiftvln-habitat-3b-1ep-f32s4-overlap0-pf-h8-pool-s2-noembed

Base model

Qwen/Qwen2.5-VL-3B-Instruct

Finetuned

(900)

this model