Instructions to use damfle/ornith-9b-custom with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use damfle/ornith-9b-custom with Transformers:

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

pipe = pipeline("image-text-to-text", model="damfle/ornith-9b-custom")
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("damfle/ornith-9b-custom")
model = AutoModelForMultimodalLM.from_pretrained("damfle/ornith-9b-custom", 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 damfle/ornith-9b-custom with vLLM:

Install from pip and serve model

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

SGLang

How to use damfle/ornith-9b-custom 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 "damfle/ornith-9b-custom" \
    --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": "damfle/ornith-9b-custom",
		"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 "damfle/ornith-9b-custom" \
        --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": "damfle/ornith-9b-custom",
		"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 damfle/ornith-9b-custom with Docker Model Runner:
```
docker model run hf.co/damfle/ornith-9b-custom
```

ornith-9b-custom / README.md

damfle

Update README.md

fafd7c4 verified 14 days ago

preview code

Raw

History Blame Contribute Delete

2.31 kB

	---
	license: isc
	datasets:
	- damfle/private-multistral-compiled-datasets
	- mlabonne/open-perfectblend
	language:
	- fr
	- en
	base_model:
	- ornith-ai/Ornith-1.0-9B
	library_name: transformers
	---
	# Ornith-9B Custom

	A fine-tuned version of [Ornith-1.0-9B](https://huggingface.co/ornith-ai/Ornith-1.0-9B) by [Damien FLETY](https://huggingface.co/damfle).

	---

	## Model Details

	- Base Model: [Ornith-1.0-9B](https://huggingface.co/ornith-ai/Ornith-1.0-9B)
	- Fine-tuned by: [damfle](https://huggingface.co/damfle)
	- License: Inherits the license of the base model (check [Ornith-1.0-9B](https://huggingface.co/ornith-ai/Ornith-1.0-9B) for details).
	- Quantization: Optimized for 4-bit quantization (QAT) and FP8 training. (soon)

	---

	## Intended Use

	This model is designed for:

	- Efficient inference in quantized (4-bit) form. (soon)
	- Integration into RAG (Retrieval-Augmented Generation) pipelines.

	---

	## Training Configuration

	- Dataset: Custom dataset (details not specified).
	- Training Approach:
	- Quantization-Aware Training (QAT) for 4-bit inference.
	- Optimizer: Muon optimizer (preferred for efficiency).

	---

	## Performance

	- Inference: Optimized for low-latency, high-throughput inference in quantized form. (dspark soon)

	---

	## How to Use

	### Inference (4-bit Quantized)

	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer

	model_name = "damfle/ornith-9b-custom"
	tokenizer = AutoTokenizer.from_pretrained(model_name)
	model = AutoModelForCausalLM.from_pretrained(
	model_name,
	device_map="auto",
	load_in_4bit=True,
	bnb_4bit_compute_dtype=torch.float16
	)

	input_text = "Your prompt here"
	inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
	outputs = model.generate(**inputs, max_new_tokens=100)
	print(tokenizer.decode(outputs[0], skip_special_tokens=True))
	```


	## Notes

	- This model is part of an iterative process to merge embeddings for a transformers architecture while keeping embedding models separate for RAG.
	- Future plans include scaling to a 16B QAT 4-bit model.

	---

	## Acknowledgments

	- Base model: [Ornith-1.0-9B](https://huggingface.co/ornith-ai/Ornith-1.0-9B) by [Ornith AI](https://huggingface.co/ornith-ai).
	- Fine-tuning and optimizations by [Damien FLETY](https://huggingface.co/damfle).