Instructions to use Sahibnoor1/gi-endoscopy-grounded-vlm-checkpoints with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sahibnoor1/gi-endoscopy-grounded-vlm-checkpoints with Transformers:

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

pipe = pipeline("image-text-to-text", model="Sahibnoor1/gi-endoscopy-grounded-vlm-checkpoints")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Sahibnoor1/gi-endoscopy-grounded-vlm-checkpoints", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Sahibnoor1/gi-endoscopy-grounded-vlm-checkpoints with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sahibnoor1/gi-endoscopy-grounded-vlm-checkpoints"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Sahibnoor1/gi-endoscopy-grounded-vlm-checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Sahibnoor1/gi-endoscopy-grounded-vlm-checkpoints

SGLang

How to use Sahibnoor1/gi-endoscopy-grounded-vlm-checkpoints 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 "Sahibnoor1/gi-endoscopy-grounded-vlm-checkpoints" \
    --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": "Sahibnoor1/gi-endoscopy-grounded-vlm-checkpoints",
		"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 "Sahibnoor1/gi-endoscopy-grounded-vlm-checkpoints" \
        --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": "Sahibnoor1/gi-endoscopy-grounded-vlm-checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Sahibnoor1/gi-endoscopy-grounded-vlm-checkpoints with Docker Model Runner:
```
docker model run hf.co/Sahibnoor1/gi-endoscopy-grounded-vlm-checkpoints
```

gi-endoscopy-grounded-vlm-checkpoints / SHA256SUMS

Sahibnoor1

Upload GI VLM checkpoints and bridge ablations

13c1769 verified about 2 months ago

Raw History Blame Contribute Delete

1.31 kB

	a1f16b9208723bc9f7d9d23ef9b1b07d7e26d6cf7f653bca53a0562f9f213bc8 ./README.md
	132c2c11c7767fdcca88af032ab90c049636235ce9adb58f37a57a3caf4ce89c ./ablations/so400m-direct-bridge/checkpoint-500/visual_bridge.safetensors
	a36a8e1a842ccbd5cbe74d2926e8ca37864380caec9395cfb8eec15482085dcb ./ablations/so400m-direct-bridge/checkpoint-500/visual_bridge_config.json
	393e8cd2654cf2c7447ba99079eb109598502f7ec23217e99bd8a8c3dd6e384e ./ablations/so400m-fixed64-distillation/final/visual_bridge.safetensors
	fa5fa2d2e0440f0a9e2fc2c0f2bce1719fca51dbf17672c0014a6606244b72f1 ./ablations/so400m-fixed64-distillation/final/visual_bridge_config.json
	2a61d525b88742d6838a84584211de4c37c296f337096f62c536da21e35007e8 ./ablations/so400m-fixed64-distillation/run_config.json
	ca814b35b71607b9a7a92ca9d31f242f02f809a5e371676cd4b6ec527e52bdef ./ablations/so400m-fixed64-distillation/val100_metrics.json
	07b0e60f1669f0515810ca4b6f842ef235e822dc4ecbce395013cdb792764aef ./qwen3-vl-8b-lora/sqrt-balanced-seed42/checkpoint-400/adapter_config.json
	8aaae10035b1f371bb8e782291e6c3996b9ca7f3f8b67b3b961fad35c47ca027 ./qwen3-vl-8b-lora/sqrt-balanced-seed42/checkpoint-400/adapter_model.safetensors
	11d8d9a4147f7203ae4a85acb8bf1a66d3702b639e811595541d09b8bb28a13b ./qwen3-vl-8b-lora/sqrt-balanced-seed42/checkpoint-400/trainer_state.json