Instructions to use Blazed-Forge/Ateron_Symphony with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Blazed-Forge/Ateron_Symphony with Transformers:

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

pipe = pipeline("text-generation", model="Blazed-Forge/Ateron_Symphony")
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("Blazed-Forge/Ateron_Symphony")
model = AutoModelForMultimodalLM.from_pretrained("Blazed-Forge/Ateron_Symphony")
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 Blazed-Forge/Ateron_Symphony with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Blazed-Forge/Ateron_Symphony

SGLang

How to use Blazed-Forge/Ateron_Symphony 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 "Blazed-Forge/Ateron_Symphony" \
    --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": "Blazed-Forge/Ateron_Symphony",
		"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 "Blazed-Forge/Ateron_Symphony" \
        --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": "Blazed-Forge/Ateron_Symphony",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Blazed-Forge/Ateron_Symphony with Docker Model Runner:
```
docker model run hf.co/Blazed-Forge/Ateron_Symphony
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Symphony

This is an experimental merge of Gemma 4, made with simple linear method. Ties shown some issues, so we roll with it instead.

Models Merged

The following models were included in the merge:

AuriAetherwiing/G4-31B-Musica-v1
ConicCat/Gemma4-GarnetV2-31B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: ./GarnetV2-31B
    parameters:
      weight: 0.75
  - model: ./G4-Musica-v1
    parameters:
      weight: 0.25
merge_method: linear
dtype: float32
out_dtype: bfloat16

Downloads last month: 108

Safetensors

Model size

31B params

Tensor type

BF16

Model tree for Blazed-Forge/Ateron_Symphony

AuriAetherwiing/G4-31B-Musica-v1

ConicCat/Gemma4-GarnetV2-31B

Merge model

this model

Quantizations

1 model