Instructions to use juspay/xor-omni with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use juspay/xor-omni with Transformers:

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

pipe = pipeline("image-text-to-text", model="juspay/xor-omni")
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)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("juspay/xor-omni")
model = AutoModelForMultimodalLM.from_pretrained("juspay/xor-omni", 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=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use juspay/xor-omni with vLLM:

Install from pip and serve model

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

SGLang

How to use juspay/xor-omni 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 "juspay/xor-omni" \
    --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": "juspay/xor-omni",
		"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 "juspay/xor-omni" \
        --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": "juspay/xor-omni",
		"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 juspay/xor-omni with Docker Model Runner:
```
docker model run hf.co/juspay/xor-omni
```

SirajRLX commited on Sep 29

Commit

a05bba6

verified ·

1 Parent(s): 30aac53

Add model card metadata and usage documentation

Browse files

Files changed (1) hide show

README.md +75 -8

README.md CHANGED Viewed

@@ -1,11 +1,78 @@
-# xor-omni
-`xor-omni` is a 26B multimodal decision model fine-tuned from `google/gemma-4-26B-A4B-it`.
-- Architecture: `Gemma4ForConditionalGeneration`
-- Precision: `bfloat16`
-- Context length: `32768`
-- Modalities: text, image, audio, video
-- Inference: SGLang
-This repository contains the merged model only. Training scripts, benchmark artifacts, adapters, and logs are intentionally not included.

+---
+license: apache-2.0
+base_model: google/gemma-4-26B-A4B-it
+library_name: transformers
+pipeline_tag: image-text-to-text
+inference: false
+tags:
+  - sglang
+  - gemma4
+  - multimodal
+  - mixture-of-experts
+  - typed-classification
+  - conversational
+  - text-generation-inference
+  - safetensors
+---
+# XOR Omni
+XOR Omni (`xor-omni`) is a multimodal decision model post-trained from [google/gemma-4-26B-A4B-it](https://huggingface.co/google/gemma-4-26B-A4B-it). It is designed for typed decision tasks and structured one-pass readout.
+## Model details
+| Field | Value |
+|---|---|
+| Base model | `google/gemma-4-26B-A4B-it` |
+| Architecture | Gemma 4 multimodal mixture-of-experts |
+| Parameters | Approximately 26B total, about 4B active per token |
+| Released precision | BF16 |
+| Context length | 32,768 tokens |
+| Input modalities | Text and image |
+| Output | Text |
+| Runtime | SGLang |
+| License | Apache License 2.0 |
+| Packaging | Fully merged weights; no adapter loading is required |
+## Intended use
+XOR Omni is intended for typed decision workloads, including:
+- Binary decisions
+- Categorical choices
+- Ordinal scoring
+- Structured readout from combined text and image context
+It is optimized for deterministic, one-pass decision output rather than open-ended assistant conversation.
+## Quick start
+Download the model:
+```bash
+hf download juspay/xor-omni --local-dir xor-omni
+```
+Example SGLang launch:
+```bash
+python -m sglang.launch_server \
+  --model-path ./xor-omni \
+  --trust-remote-code \
+  --context-length 32768 \
+  --host 0.0.0.0 \
+  --port 30000
+```
+Use the included `chat_template.jinja` when serving the model. The exact deployment configuration should be validated for your target hardware and workload.
+## Limitations
+- This model is specialized for typed decision tasks and is not intended as a general-purpose assistant.
+- Multimodal behavior should be validated on your own data before production use.
+- Performance may vary with prompt format, context length, hardware, and serving configuration.
+- This repository contains merged model weights only; training scripts, adapters, benchmark artifacts, and logs are intentionally not included.
+## License
+This model is released under the Apache License 2.0, inherited from the base Gemma 4 checkpoint.