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

Libraries

How to use SL-AI/GRaPE-2.5-Quasar 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-Quasar")
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-Quasar")
model = AutoModelForMultimodalLM.from_pretrained("SL-AI/GRaPE-2.5-Quasar", 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-Quasar 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-Quasar"
# 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-Quasar",
		"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-Quasar

SGLang

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

I wanted a drawing and it actually gave a fuck 😂

by owao - opened 19 days ago

Discussion

owao

19 days ago

owao changed discussion title from I wanted a drawing but it gave me a middle finger instead to I wanted a drawing and it actually gave a fuck 19 days ago

DedeProGames

19 days ago

@owao Could you give me the prompt?

owao

19 days ago

Wasn't meant to be taken seriously 😅

But here, for simple for smoke test:

Write the SVG code for a detailed sci‑fi scene featuring a boy standing by the window, staring out at his planet's multi‑moon system. The ambiance inside is warm and cozy, and the planetary system welcoming. <thinking_mode=xtra-hi>

owao changed discussion title from I wanted a drawing and it actually gave a fuck to I wanted a drawing and it actually gave a fuck 😂 19 days ago

owao

19 days ago

If you really interested, config was:

  "GRaPE-2.5-Quasar":
    env:
      - "CUDA_VISIBLE_DEVICES=0"
    cmd: |
      /home/user/llama.cpp/build/bin/llama-server
      --model /mnt/storage/GGUFs/Qwen3.8-27B/GRaPE-2.5-Quasar.Q6_K.gguf
      --model-draft /mnt/storage/GGUFs/Qwen3.8-27B/mtp-Qwen3.8-27B-Q4_0.gguf
      --mmproj /mnt/storage/GGUFs/Qwen3.8-27B/mmproj-BF16.gguf
      --image-max-tokens 16384
      -lv 4
      --webui-mcp-proxy
      --tools all
      --no-warmup
      --ctx-size 100000
      --no-context-shift
      --n-gpu-layers 66
      --temp 1
      --top-p 0.95
      --top-k 20
      --min-p 0
      # --presence-penalty 0.2
      --repeat-penalty 1
      --jinja
      --host 0.0.0.0
      --port ${PORT}
      --flash-attn on
      # --mlock
      --ctx-checkpoints 64
      --parallel 1
      --spec-type draft-mtp
      --spec-draft-n-max 8
      --spec-draft-p-min 0
      # --backend-sampling

Sweaterdog

Skinnertopia Lab for Artifical Intelligence org 19 days ago

Glad to see Quasar's creativity is poking through!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment