Instructions to use SL-AI/GRaPE-2.1-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SL-AI/GRaPE-2.1-Flash with Transformers:

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

pipe = pipeline("image-text-to-text", model="SL-AI/GRaPE-2.1-Flash")
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 AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("SL-AI/GRaPE-2.1-Flash")
model = AutoModelForImageTextToText.from_pretrained("SL-AI/GRaPE-2.1-Flash")
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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use SL-AI/GRaPE-2.1-Flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SL-AI/GRaPE-2.1-Flash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SL-AI/GRaPE-2.1-Flash",
		"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/SL-AI/GRaPE-2.1-Flash

SGLang

How to use SL-AI/GRaPE-2.1-Flash 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 "SL-AI/GRaPE-2.1-Flash" \
    --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": "SL-AI/GRaPE-2.1-Flash",
		"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 "SL-AI/GRaPE-2.1-Flash" \
        --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": "SL-AI/GRaPE-2.1-Flash",
		"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 SL-AI/GRaPE-2.1-Flash with Docker Model Runner:
```
docker model run hf.co/SL-AI/GRaPE-2.1-Flash
```

Sweaterdog commited on Apr 24

Commit

0161c23

verified ·

1 Parent(s): 8ae5369

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -18

README.md CHANGED Viewed

@@ -103,24 +103,6 @@ Scores sourced from official technical reports (Qwen3 Technical Report, May 2025
 > **Note:** *Benchmarks are Underway for GRaPE 2.1 Flash, they will be empty and set as "TBD" for the time being*
-### Benchmarks
-| Models               | Params            | GPQA Diamond | MMLU-Pro | LiveCodeBench v6 | HMMT Nov 25 | TAU2-Bench | MultiChallenge |
-|----------------------|-------------------|--------------|----------|------------------|-------------|------------|----------------|
-| GRaPE 2.1 Flash      | 9B                | TBD          | TBD      | TBD              | TBD         | TBD        | TBD            |
-| GRM-2.5-Plus         | 9B                | 82.7         | 84.2     | 67.2             | 83.2        | 80.5       | 56.5           |
-| Qwen3.5-9B           | 9B                | 81.7         | 82.5     | 65.6             | 82.9        | 79.1       | 54.5           |
-| google/gemma-4-E4B-it| E4B (4.5B eff.)   | 58.6         | 69.4     | 52.0             | --          | 42.2       | --             |
-***
-### Real World Example
-I know benchmarks seem cool on paper, but some people like to demo models by themselves. I asked GRaPE 2.1 Flash to make a webpage for Aurora Beats, and you can find that [here](https://huggingface.co/SL-AI/GRaPE-2.1-Flash_GGUF/raw/main/Aurora_Beats_2.1_flash.html)
-***
 # Recommended Inference Settings
 Tested in **LM Studio**. These sampling parameters are a good starting point:

 > **Note:** *Benchmarks are Underway for GRaPE 2.1 Flash, they will be empty and set as "TBD" for the time being*
 # Recommended Inference Settings
 Tested in **LM Studio**. These sampling parameters are a good starting point: