Instructions to use tepirale/Ornith-Agents-A1-3.7-35B-A3B-dare_ties_v4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tepirale/Ornith-Agents-A1-3.7-35B-A3B-dare_ties_v4 with Transformers:

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

pipe = pipeline("image-text-to-text", model="tepirale/Ornith-Agents-A1-3.7-35B-A3B-dare_ties_v4")
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("tepirale/Ornith-Agents-A1-3.7-35B-A3B-dare_ties_v4")
model = AutoModelForMultimodalLM.from_pretrained("tepirale/Ornith-Agents-A1-3.7-35B-A3B-dare_ties_v4")
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 tepirale/Ornith-Agents-A1-3.7-35B-A3B-dare_ties_v4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tepirale/Ornith-Agents-A1-3.7-35B-A3B-dare_ties_v4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tepirale/Ornith-Agents-A1-3.7-35B-A3B-dare_ties_v4",
		"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/tepirale/Ornith-Agents-A1-3.7-35B-A3B-dare_ties_v4

SGLang

How to use tepirale/Ornith-Agents-A1-3.7-35B-A3B-dare_ties_v4 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 "tepirale/Ornith-Agents-A1-3.7-35B-A3B-dare_ties_v4" \
    --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": "tepirale/Ornith-Agents-A1-3.7-35B-A3B-dare_ties_v4",
		"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 "tepirale/Ornith-Agents-A1-3.7-35B-A3B-dare_ties_v4" \
        --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": "tepirale/Ornith-Agents-A1-3.7-35B-A3B-dare_ties_v4",
		"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 tepirale/Ornith-Agents-A1-3.7-35B-A3B-dare_ties_v4 with Docker Model Runner:
```
docker model run hf.co/tepirale/Ornith-Agents-A1-3.7-35B-A3B-dare_ties_v4
```

How do we make Quants of this merge?

by NeatOnTheRocks - opened 2 days ago

Discussion

NeatOnTheRocks

2 days ago

I'm new to using merges like this and relatively new to the scene in general. If I wanted to simply create and use a Q4_K_M quant of this, how would I go about doing so? Forgive the ignorance.

tepirale

Owner 2 days ago

Hi, here's a document that would explain it better than I can:

https://github.com/ggml-org/llama.cpp/blob/master/tools/quantize/README.md

NeatOnTheRocks

1 day ago

Thanks for the response, but I should have been more specific: I've tried using the "GGUF-my-repo" space but get the following error:

tepirale

Owner 1 day ago

Hi,

It's asking you to update, but I'm not sure which version of Transformers and llama.cpp you have.

Update Transformers:
pip install --upgrade --force-reinstall transformers

Also update llama.cpp if necessary.

You should also know that the model you downloaded, 'tepirale/Ornith-Agents-A1-3.7-35B-A3B-dare_ties_v4', doesn't have an internal MTP layer because I forgot to add the 'Flag' to include it internally. Therefore, the MTP and Vision layers are external in this case.

MTP layer

https://huggingface.co/tepirale/Ornith-Agents-A1-3.6-35B-A3B-MTP-GGUF/blob/main/Ornith-Agents-A1-3.6-35B-A3B-dare_ties-mtp-sidecar.gguf

Vision layer

https://huggingface.co/tepirale/Ornith-Agents-A1-3.6-35B-A3B-MTP-GGUF/blob/main/mmproj-F32.gguf

--mmproj mmproj-F32.gguf
-md Ornith-Agents-A1-3.6-35B-A3B-dare_ties-mtp-sidecar.gguf

tepirale

Owner 1 day ago

If you solve it, great, but if life allows, I'll upload the GGUF tomorrow or the day after.

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