Instructions to use ornith-ai/Ornith-1.5-35B-A3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ornith-ai/Ornith-1.5-35B-A3B with Transformers:

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

pipe = pipeline("text-generation", model="ornith-ai/Ornith-1.5-35B-A3B")
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-1.5-35B-A3B")
model = AutoModelForMultimodalLM.from_pretrained("ornith-ai/Ornith-1.5-35B-A3B", 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-1.5-35B-A3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ornith-ai/Ornith-1.5-35B-A3B"
# 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-1.5-35B-A3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ornith-ai/Ornith-1.5-35B-A3B

SGLang

How to use ornith-ai/Ornith-1.5-35B-A3B 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-1.5-35B-A3B" \
    --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-1.5-35B-A3B",
		"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-1.5-35B-A3B" \
        --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-1.5-35B-A3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ornith-ai/Ornith-1.5-35B-A3B with Docker Model Runner:
```
docker model run hf.co/ornith-ai/Ornith-1.5-35B-A3B
```

model-00016-of-00016.safetensors was just updated... What?

#25

by pathosethoslogos - opened 3 days ago

Discussion

pathosethoslogos

3 days ago

I couldn't find any explanation or announcement. Any info?

felkf

3 days ago

https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B/discussions/10#6a86fe589da29f742c7b4c25

#10 issue is there

pathosethoslogos

3 days ago

https://huggingface.co/ornith-ai/Ornith-1.5-35B-A3B/discussions/10#6a86fe589da29f742c7b4c25

#10 issue is there

Oh, so does this mean MTP can be enabled now?

I thought MTPs needed to be separate a model.

zxbc2023

1 day ago

Oh, so does this mean MTP can be enabled now?

I thought MTPs needed to be separate a model.

The baked in MTP in this model was faulty - tensors were randomly initiated and not trained. Ornith did not publicize this error - quite the contrary, they closed the thread that alerted the public of this. Then they stealth fixed the tensors (allegedly) through an update without announcing it. So now, the source model has been changed, but the quants already inherited the bad version of MTP. Luckily many quants have supplied information or direct link on obtaining trained MTPs, you just have to look a little more carefully what you're downloading.

Very disappointed in how Ornith handled the fiasco.

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