Instructions to use aimeri/spoomplesmaxx-magpie-35B-A3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aimeri/spoomplesmaxx-magpie-35B-A3 with Transformers:

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

pipe = pipeline("text-generation", model="aimeri/spoomplesmaxx-magpie-35B-A3")
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("aimeri/spoomplesmaxx-magpie-35B-A3")
model = AutoModelForMultimodalLM.from_pretrained("aimeri/spoomplesmaxx-magpie-35B-A3", 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 aimeri/spoomplesmaxx-magpie-35B-A3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aimeri/spoomplesmaxx-magpie-35B-A3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aimeri/spoomplesmaxx-magpie-35B-A3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aimeri/spoomplesmaxx-magpie-35B-A3

SGLang

How to use aimeri/spoomplesmaxx-magpie-35B-A3 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 "aimeri/spoomplesmaxx-magpie-35B-A3" \
    --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": "aimeri/spoomplesmaxx-magpie-35B-A3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "aimeri/spoomplesmaxx-magpie-35B-A3" \
        --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": "aimeri/spoomplesmaxx-magpie-35B-A3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aimeri/spoomplesmaxx-magpie-35B-A3 with Docker Model Runner:
```
docker model run hf.co/aimeri/spoomplesmaxx-magpie-35B-A3
```

Scarily smart

by Koshkasa - opened 10 days ago

Discussion

Koshkasa

10 days ago

Following my general disappointment in small Qwen MoE as a roleplay platform, this tune repeatedly punches far above its active parameter weight. This is based on "feels" as opposed to any objective metric, but the "feels" are that it maintains scene and character coherence better than stock Qwen 27B dense tunes, runs laps around Gemma 4 26B in terms of language, and gets creative enough to tie Mistral 24b in my improvised A/B testing.

Looks to be a hidden 12-16G gem so far.

aimeri

Owner 4 days ago

Thank you so much for the kind words! I definitely enjoyed this one as well. Thank you so much for using my models!

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