Eku127
/

openfly-satnav-scratch-1ep-actcompact-sample-hk7-fs3-stopx2-stopw0-tail5-stoph1-hist16-lr2e-5

Instructions to use Eku127/openfly-satnav-scratch-1ep-actcompact-sample-hk7-fs3-stopx2-stopw0-tail5-stoph1-hist16-lr2e-5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Eku127/openfly-satnav-scratch-1ep-actcompact-sample-hk7-fs3-stopx2-stopw0-tail5-stoph1-hist16-lr2e-5 with Transformers:

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

pipe = pipeline("image-text-to-text", model="Eku127/openfly-satnav-scratch-1ep-actcompact-sample-hk7-fs3-stopx2-stopw0-tail5-stoph1-hist16-lr2e-5")

# pip install -U transformers accelerate
# Load model directly
from transformers import OpenVLAForActionPrediction
model = OpenVLAForActionPrediction.from_pretrained("Eku127/openfly-satnav-scratch-1ep-actcompact-sample-hk7-fs3-stopx2-stopw0-tail5-stoph1-hist16-lr2e-5", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Eku127/openfly-satnav-scratch-1ep-actcompact-sample-hk7-fs3-stopx2-stopw0-tail5-stoph1-hist16-lr2e-5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Eku127/openfly-satnav-scratch-1ep-actcompact-sample-hk7-fs3-stopx2-stopw0-tail5-stoph1-hist16-lr2e-5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Eku127/openfly-satnav-scratch-1ep-actcompact-sample-hk7-fs3-stopx2-stopw0-tail5-stoph1-hist16-lr2e-5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Eku127/openfly-satnav-scratch-1ep-actcompact-sample-hk7-fs3-stopx2-stopw0-tail5-stoph1-hist16-lr2e-5

SGLang

How to use Eku127/openfly-satnav-scratch-1ep-actcompact-sample-hk7-fs3-stopx2-stopw0-tail5-stoph1-hist16-lr2e-5 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/openfly-satnav-scratch-1ep-actcompact-sample-hk7-fs3-stopx2-stopw0-tail5-stoph1-hist16-lr2e-5" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Eku127/openfly-satnav-scratch-1ep-actcompact-sample-hk7-fs3-stopx2-stopw0-tail5-stoph1-hist16-lr2e-5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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/openfly-satnav-scratch-1ep-actcompact-sample-hk7-fs3-stopx2-stopw0-tail5-stoph1-hist16-lr2e-5" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Eku127/openfly-satnav-scratch-1ep-actcompact-sample-hk7-fs3-stopx2-stopw0-tail5-stoph1-hist16-lr2e-5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Eku127/openfly-satnav-scratch-1ep-actcompact-sample-hk7-fs3-stopx2-stopw0-tail5-stoph1-hist16-lr2e-5 with Docker Model Runner:
```
docker model run hf.co/Eku127/openfly-satnav-scratch-1ep-actcompact-sample-hk7-fs3-stopx2-stopw0-tail5-stoph1-hist16-lr2e-5
```

OpenFly for SatNav — Base initialization

This checkpoint is designed for use with SatNav, the continuous-state vision-and-language navigation platform for satellite maps. The SatNav OpenFly integration uses it to predict the next action from a language instruction, three RGB observations, and recent action history.

Model

Starting checkpoint: openvla/openvla-7b-prismatic with OpenFly processor assets
Training data: SatNav-v0.1 offline trajectories
Training: 1 epoch, full-parameter fine-tuning, learning rate 2e-5
Context: 3 RGB frames and up to 16 previous actions
Action format: stop, forward, left, and right

Repository name

openfly-satnav: OpenFly adapted to SatNav
scratch: base initialization from the OpenVLA checkpoint with OpenFly processor assets
1ep: trained for one epoch
actcompact: predicts compact textual action labels
sample: the following fields describe trajectory-step sampling
hk7: keeps the first seven action steps
fs3: keeps every third step in a consecutive forward run; turning steps are kept
stopx2: repeats each stop sample twice
stopw0: labels only the terminal step as stop
tail5: keeps the final five steps before stop
stoph1: uses one history variant for each stop sample
hist16: includes up to 16 previous actions in the prompt
lr2e-5: uses a learning rate of 2e-5

Reference Results

Results reported in the SatNav paper, baseline comparison, row OpenFly.

SR, SPL, and OS are percentages. NE is measured in meters. Steps is the average number of executed environment actions, including turns and stop.

Split	SR (%)	SPL (%)	OS (%)	NE (m)	Steps
Test Seen (`val_seen`)	13.2	13.0	33.5	166.88	58.93
Test Unseen (`val_unseen`)	11.7	11.6	32.2	195.91	66.35

Usage

Use this checkpoint with the SatNav OpenFly integration. It is also listed in the SatNav Baseline Model Zoo.

License

The checkpoint is released under MIT. OpenFly, OpenVLA, underlying model components, SatNav, and datasets remain subject to their respective terms.

Downloads last month: 25

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for Eku127/openfly-satnav-scratch-1ep-actcompact-sample-hk7-fs3-stopx2-stopw0-tail5-stoph1-hist16-lr2e-5

Base model

openvla/openvla-7b-prismatic

Finetuned

IPEC-COMMUNITY/openfly-agent-7b

Finetuned

(2)

this model

Collection including Eku127/openfly-satnav-scratch-1ep-actcompact-sample-hk7-fs3-stopx2-stopw0-tail5-stoph1-hist16-lr2e-5

SatNav Baseline Model Zoo

Collection

Baseline checkpoints for SatNav vision-language navigation. This collection includes StreamVLN, OpenFly, UniNaVid, and NaVILA • 8 items • Updated Jul 4 • 1