Instructions to use ornith-ai/Ornith-1.0-35B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ornith-ai/Ornith-1.0-35B with Transformers:

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

pipe = pipeline("text-generation", model="ornith-ai/Ornith-1.0-35B")
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("ornith-ai/Ornith-1.0-35B")
model = AutoModelForMultimodalLM.from_pretrained("ornith-ai/Ornith-1.0-35B", 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 ornith-ai/Ornith-1.0-35B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ornith-ai/Ornith-1.0-35B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ornith-ai/Ornith-1.0-35B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ornith-ai/Ornith-1.0-35B

SGLang

How to use ornith-ai/Ornith-1.0-35B 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 "ornith-ai/Ornith-1.0-35B" \
    --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": "ornith-ai/Ornith-1.0-35B",
		"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 "ornith-ai/Ornith-1.0-35B" \
        --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": "ornith-ai/Ornith-1.0-35B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ornith-ai/Ornith-1.0-35B with Docker Model Runner:
```
docker model run hf.co/ornith-ai/Ornith-1.0-35B
```

MTP

by engrtipusultan - opened Jun 25

Discussion

engrtipusultan

Jun 25

Is there any chance of adding MTP?

skinnyctax

Jun 26

https://huggingface.co/skinnyctax/Ornith-1.0-35B-Q6_K-Frankenstein-MTP-GGUF uploading now if anyone wants to test. Details on how to do it yourself on the model card.

btvd

Jun 30

Has anyone found MTP version for vLLM serving?

engrtipusultan changed discussion status to closed Jun 30

peonist

Aug 17

Grafted the 19 mtp.* tensors from Qwen/Qwen3.6-35B-A3B onto the BF16 checkpoint for vLLM — safetensors rather than GGUF, so it complements skinnyctax's Frankenstein-MTP.

Measured on one 35B-A3B at n=2: 70.3% draft acceptance, +38.7% prose / +54.6% code decode. To @Treene 's question in #26 — the post-train does not kill acceptance. Ornith's weights are untouched (sha256-identical to upstream); only the 19 tensors are added, which also makes mtp_num_hidden_layers: 1 in config.json true.

Repo: crucible-labs/Ornith-1.0-35B-MTP. Graft script included if you'd rather build it yourself from your own copy. Costs ~21.8% KV capacity; keep num_speculative_tokens ≤ 4.

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