Instructions to use SL-AI/GRaPE-2.5-Helios with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SL-AI/GRaPE-2.5-Helios with Transformers:

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

pipe = pipeline("image-text-to-text", model="SL-AI/GRaPE-2.5-Helios")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("SL-AI/GRaPE-2.5-Helios")
model = AutoModelForMultimodalLM.from_pretrained("SL-AI/GRaPE-2.5-Helios", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SL-AI/GRaPE-2.5-Helios with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SL-AI/GRaPE-2.5-Helios"
# 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-2.5-Helios",
		"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-2.5-Helios

SGLang

How to use SL-AI/GRaPE-2.5-Helios 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-2.5-Helios" \
    --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-2.5-Helios",
		"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-2.5-Helios" \
        --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-2.5-Helios",
		"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-2.5-Helios with Docker Model Runner:
```
docker model run hf.co/SL-AI/GRaPE-2.5-Helios
```

Sweaterdog commited on 20 days ago

Commit

2dbb858

verified ·

1 Parent(s): cd7a521

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -4

README.md CHANGED Viewed

@@ -46,7 +46,7 @@ _The **G**eneral **R**easoning **A**gent (for) **P**roject **E**xploration_
 # GRaPE 2.5 Helios
-**GRaPE 2.5 Helios** is the mid-sized model of the second-generation GRaPE family, it supports multimodal inputs (image + text) and features controllable thinking modes, and work efforts for agentic tasks.
 GRaPE 2.5 Helios is the direct successor to GRaPE 2.1 Flash, carrying forward research and reasoning improvements from the second generation while incorporating substantially improved training data, focusing on data quality over quantity.
@@ -153,9 +153,9 @@ If the work effort is left blank, GRaPE 2.5 Helios will automatically decide on
 Work effort only works when the agent has access to tools. Otherwise, it will use `minimal`, regardless of the user-defined thinking modes.
-> **Tip:** GRaPE 2.5 Helios had a large amount of agent training done in our agent harness, **Scribe,** recommend it for best performance.
-To learn more about Scribe, visit the product page [Here.](https://grape.skinnertopia.com/products/scribe)
 ***
@@ -181,7 +181,7 @@ When you ask a model, "Make a website for yourself," you likely don't want to se
 We focused a large sum of the training corpus on the models' ability to construct **creative conversations,** and **write stories.** As found from previous Openprose models, GRaPE 2.5 models have the greatest creative capability out of any prior model.
-During early experimental testing of GRaPE 2.5 Andromeda, we found the model would often be *too creative* for it's own good. When asked for a Browser OS app, it decided to not go for an web-based app which has a classic desktop environment. It wanted to build a ring, which every app would have an orbit around the center, and the window manager would move the apps around the orbit. The web-based browser OS had a proof-of-concept, but was very unrefined.
 Testing community-made prompts, such as Bijan Bowen's "Steve the PC-Repair Man" game, the same experimental version of GRaPE 2.5 Quasar built the game, but kept finding new, and creative features, and most importantly, **did not give up.**
@@ -194,6 +194,8 @@ GRaPE 2.5 models was our first adventure into jointly boosting a model's creativ
 - Training data is closed-source and proprietary.
 - Updates and announcements are posted on [Skinnertopia](https://www.skinnertopia.com/)
 GRaPE 2.5 is likely one of the last models SLAI will produce for simply being a finetune on-top of another model. We will conduct further research and release experimental GRaPE 3 models.
 We appreciate you all for the continued support and appreciation for GRaPE models.

 # GRaPE 2.5 Helios
+**GRaPE 2.5 Helios** is the mid-sized model of the third-generation GRaPE family, it supports multimodal inputs (image + text) and features controllable thinking modes, and work efforts for agentic tasks.
 GRaPE 2.5 Helios is the direct successor to GRaPE 2.1 Flash, carrying forward research and reasoning improvements from the second generation while incorporating substantially improved training data, focusing on data quality over quantity.
 Work effort only works when the agent has access to tools. Otherwise, it will use `minimal`, regardless of the user-defined thinking modes.
+> **Tip:** GRaPE 2.5 Helios had a large amount of agent training done in our agent harness, **Scribe,** we recommend it for best performance.
+To learn more about Scribe, and download it, visit the product page [Here.](https://skinnertopia.com/products/scribe)
 ***
 We focused a large sum of the training corpus on the models' ability to construct **creative conversations,** and **write stories.** As found from previous Openprose models, GRaPE 2.5 models have the greatest creative capability out of any prior model.
+During early experimental testing of GRaPE 2.5 Quasar, we found the model would often be *too creative* for it's own good. When asked for a Browser OS app, it decided to not go for an web-based app which has a classic desktop environment. It wanted to build a ring, which every app would have an orbit around the center, and the window manager would move the apps around the orbit. The web-based browser OS had a proof-of-concept, but was very unrefined.
 Testing community-made prompts, such as Bijan Bowen's "Steve the PC-Repair Man" game, the same experimental version of GRaPE 2.5 Quasar built the game, but kept finding new, and creative features, and most importantly, **did not give up.**
 - Training data is closed-source and proprietary.
 - Updates and announcements are posted on [Skinnertopia](https://www.skinnertopia.com/)
+Unless there is strong demand, we will *not* be releasing any other model sizes for the GRaPE 2.5 family, and instead focus on GRaPE 3 models.
 GRaPE 2.5 is likely one of the last models SLAI will produce for simply being a finetune on-top of another model. We will conduct further research and release experimental GRaPE 3 models.
 We appreciate you all for the continued support and appreciation for GRaPE models.