Instructions to use Vortex5/Chimera-X-26B-A4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Vortex5/Chimera-X-26B-A4B with Transformers:

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

pipe = pipeline("image-text-to-text", model="Vortex5/Chimera-X-26B-A4B")
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("Vortex5/Chimera-X-26B-A4B")
model = AutoModelForMultimodalLM.from_pretrained("Vortex5/Chimera-X-26B-A4B", 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 Vortex5/Chimera-X-26B-A4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Vortex5/Chimera-X-26B-A4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Vortex5/Chimera-X-26B-A4B",
		"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/Vortex5/Chimera-X-26B-A4B

SGLang

How to use Vortex5/Chimera-X-26B-A4B 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 "Vortex5/Chimera-X-26B-A4B" \
    --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": "Vortex5/Chimera-X-26B-A4B",
		"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 "Vortex5/Chimera-X-26B-A4B" \
        --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": "Vortex5/Chimera-X-26B-A4B",
		"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 Vortex5/Chimera-X-26B-A4B with Docker Model Runner:
```
docker model run hf.co/Vortex5/Chimera-X-26B-A4B
```

Quants?

by Iloqt - opened 13 days ago

Discussion

Iloqt

13 days ago

Did you need somebody to quantize this for you? I dig your 26B Moonlight, I can quantize this one for you if you wish.

Vortex5

Owner 13 days ago

Did you need somebody to quantize this for you? I dig your 26B Moonlight, I can quantize this one for you if you wish.

Thanks for the offer. I already have a quant request with mradermacher. I am happy to hear you liked G4-Moonlight-Dusk-26B-A4B!

mradermacher

13 days ago

just came here to find out more, because i have a tab open for this model for two days (somebody else manages the messages, so i was not aware), but i queued it up two days ago already. and it failed, and I removed it, because at the time it was not requested. but kept the tab open because it looked interesting. and for some reason this post made me realise I made a mistakle quantizing it, which is why it failed. anyway, attempt #2 is happening right now...

Vortex5

Owner 13 days ago

@mradermacher Thanks for trying, I see attempt 2 failed. I was able to make quant for myself to test with latest llama.cpp version. I am unsure what went wrong.

mradermacher

12 days ago

•

edited 12 days ago

the failure is because there is no vision component and the pipeline always tries to extract the mmproj files. we have to manually mark it as novision. i am confident it will work, given that it worked for you :)

mradermacher

12 days ago

that was it, all is fine. enjoy! i'll certainly give it a try.

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