Instructions to use ping69852/Medusa-Qwen2.5-VL-7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ping69852/Medusa-Qwen2.5-VL-7B-Instruct with Transformers:

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

pipe = pipeline("image-text-to-text", model="ping69852/Medusa-Qwen2.5-VL-7B-Instruct")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ping69852/Medusa-Qwen2.5-VL-7B-Instruct", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ping69852/Medusa-Qwen2.5-VL-7B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ping69852/Medusa-Qwen2.5-VL-7B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ping69852/Medusa-Qwen2.5-VL-7B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ping69852/Medusa-Qwen2.5-VL-7B-Instruct

SGLang

How to use ping69852/Medusa-Qwen2.5-VL-7B-Instruct 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 "ping69852/Medusa-Qwen2.5-VL-7B-Instruct" \
    --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": "ping69852/Medusa-Qwen2.5-VL-7B-Instruct",
		"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 "ping69852/Medusa-Qwen2.5-VL-7B-Instruct" \
        --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": "ping69852/Medusa-Qwen2.5-VL-7B-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ping69852/Medusa-Qwen2.5-VL-7B-Instruct with Docker Model Runner:
```
docker model run hf.co/ping69852/Medusa-Qwen2.5-VL-7B-Instruct
```

Medusa-Qwen2.5-VL-7B-Instruct

Medusa draft heads for Qwen2.5-VL-7B-Instruct.
Part of the Multimodal Speculative Decoding Benchmark.

Files

File	Description
`config.json`	Model architecture config
`pytorch_model_fsdp.bin`	Full FSDP state-dict (model weights)

Usage

Load via the medusa inference utilities in the benchmark repo.

Notes

Checkpoint: state_19
Uploaded: 2026-03-04

Downloads last month: 4

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ping69852/Medusa-Qwen2.5-VL-7B-Instruct

Base model

Qwen/Qwen2.5-VL-7B-Instruct

Finetuned

(1136)

this model