Instructions to use Atomic-Germ/Ornith-1.0-9B-NPU2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Atomic-Germ/Ornith-1.0-9B-NPU2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="Atomic-Germ/Ornith-1.0-9B-NPU2")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Atomic-Germ/Ornith-1.0-9B-NPU2")
model = AutoModelForMultimodalLM.from_pretrained("Atomic-Germ/Ornith-1.0-9B-NPU2", 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 = tokenizer.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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Atomic-Germ/Ornith-1.0-9B-NPU2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Atomic-Germ/Ornith-1.0-9B-NPU2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Atomic-Germ/Ornith-1.0-9B-NPU2",
		"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/Atomic-Germ/Ornith-1.0-9B-NPU2

SGLang

How to use Atomic-Germ/Ornith-1.0-9B-NPU2 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 "Atomic-Germ/Ornith-1.0-9B-NPU2" \
    --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": "Atomic-Germ/Ornith-1.0-9B-NPU2",
		"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 "Atomic-Germ/Ornith-1.0-9B-NPU2" \
        --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": "Atomic-Germ/Ornith-1.0-9B-NPU2",
		"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 Atomic-Germ/Ornith-1.0-9B-NPU2 with Docker Model Runner:
```
docker model run hf.co/Atomic-Germ/Ornith-1.0-9B-NPU2
```

Ornith-1.0-9B-NPU2

File size: 3,096 Bytes

{
  "architectures": [
    "Qwen3_5ForConditionalGeneration"
  ],
  "dtype": "bfloat16",
  "eos_token_id": 248046,
  "hidden_size": 4096,
  "image_token_id": 248056,
  "model_type": "qwen3_5_text",
  "pad_token_id": 248044,
  "tie_word_embeddings": false,
  "transformers_version": "5.8.1",
  "use_cache": false,
  "vision_config": {
    "vision_mm_engine_xclbin_name": "vision_mm.xclbin",
    "vision_mha_engine_xclbin_name": "vision_attn.xclbin",
    "QWEN3_5_PATCH_SIZE": 16,
    "QWEN3_5_IMAGE_MERGE_SIZE": 2,
    "QWEN3_5_SPATIAL_MERGE_SIZE": 2,
    "QWEN3_5_SHORTEST_EDGE": 65536,
    "QWEN3_5_LONGEST_EDGE": 16777216,
    "QWEN3_5_VISION_RESCALE_FACTOR": 0.00392156862745098,
    "QWEN3_5_VISION_RESCALE_IMAGE_MEAN": 0.5,
    "QWEN3_5_VISION_RESCALE_IMAGE_STD": 0.5,
    "QWEN3_5_TEMPORAL_PATCH_SIZE": 2,
    "QWEN3_5_VISION_EMBED_DIM": 1152,
    "QWEN3_5_VISION_NUM_HEADS": 16,
    "QWEN3_5_VISION_HEAD_DIM": 72,
    "QWEN3_5_VISION_MLP_INTERMEDIATE_SIZE": 4304,
    "QWEN3_5_VISION_NUM_POSITION_EMBEDDINGS": 2304,
    "QWEN3_5_VISION_NUM_LAYERS": 27,
    "QWEN3_5_VISION_LAYER_NORM_EPSILON": 1e-06,
    "QWEN3_5_VISION_OUT_HIDDEN_SIZE": 4096,
    "VISION_MM_TILE_M": 128,
    "VISION_MM_TILE_K": 256,
    "VISION_MM_TILE_N": 64
  },
  "vision_end_token_id": 248054,
  "vision_start_token_id": 248053,
  "attention_bias": false,
  "attention_dropout": 0.0,
  "attn_output_gate": true,
  "bos_token_id": 248044,
  "full_attention_interval": 4,
  "head_dim": 256,
  "hidden_act": "silu",
  "initializer_range": 0.02,
  "intermediate_size": 12288,
  "layer_types": [
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention",
    "linear_attention",
    "linear_attention",
    "linear_attention",
    "full_attention"
  ],
  "linear_conv_kernel_dim": 4,
  "linear_key_head_dim": 128,
  "linear_num_key_heads": 16,
  "linear_num_value_heads": 32,
  "linear_value_head_dim": 128,
  "mamba_ssm_dtype": "float32",
  "max_position_embeddings": 262144,
  "mlp_only_layers": [],
  "mtp_num_hidden_layers": 1,
  "mtp_use_dedicated_embeddings": false,
  "num_attention_heads": 16,
  "num_hidden_layers": 32,
  "num_key_value_heads": 4,
  "partial_rotary_factor": 0.25,
  "rms_norm_eps": 1e-06,
  "rope_parameters": {
    "mrope_interleaved": true,
    "mrope_section": [
      11,
      11,
      10
    ],
    "partial_rotary_factor": 0.25,
    "rope_theta": 10000000,
    "rope_type": "default"
  },
  "vocab_size": 248320,
  "flm_version": "1.0.1",
  "vision_model_weight": "vision_weight.q4nx"
}