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
```

After tweaking the llamacpp settings, this model is a goat (crazy good)

#23

by lolren - opened Jul 1

Discussion

lolren

Jul 1

docker run -d --gpus all
--name llama-cpp-ornith-35b-q8
--restart unless-stopped
--shm-size 32g
-p 8090:8000
-v "$MODEL_DIR:/models:ro"
ghcr.io/ggml-org/llama.cpp:server-cuda
--host 0.0.0.0
--port 8000
-m /models/ornith-1.0-35b-gguf-q8/ornith-1.0-35b-Q8_0.gguf
-c 262144
-n 16384
-b 2048
-ub 256
-ngl 99
-ts 0.55,0.45
-fa on
--cache-type-k q8_0
--cache-type-v q8_0
-np 1
--jinja
--reasoning auto
--reasoning-format deepseek
--reasoning-budget 4096
--reasoning-preserve
--chat-template-kwargs '{"preserve_thinking":true}'
--temp 0.6
--top-p 0.95
--top-k 20
--min-p 0.0
--repeat-penalty 1.08
--repeat-last-n 4096
--presence-penalty 0.0
--frequency-penalty 0.0

this works amazing for me!
2x3090
Try it!

alexanderacuna

Jul 1

Have you been able to get MTP to work during your testing?

lolren

Jul 1

The model is fast enough to care about MTP😅

lee21321

Jul 6

Why are you running on llama. cpp? Is it because of Q8 quantization? What are your respective speeds for prefill and decode?
I use VLLM to run it, although it can only run Q4 quantization to maintain the 262144 context.
When I was running Llama.cpp, I found that the prefill prompt could not hit the cache, which would take a long time for long context TTFT, and decoding speed was not worth the cost.

jackson145258116

Jul 12

Is there any actual use case you tested with the config you shared here?

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