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

Libraries

How to use juspay/xor with Transformers:

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

pipe = pipeline("text-generation", model="juspay/xor")
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")
model = AutoModelForMultimodalLM.from_pretrained("juspay/xor", 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 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "juspay/xor"
# 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",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/juspay/xor

SGLang

How to use juspay/xor 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" \
    --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",
		"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 "juspay/xor" \
        --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",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use juspay/xor with Docker Model Runner:
```
docker model run hf.co/juspay/xor
```

prakharprakash commited on 23 days ago

Commit

8a03d38

verified ·

1 Parent(s): be42456

Document multimodal serving support

Browse files

Files changed (1) hide show

README.md +11 -1

README.md CHANGED Viewed

@@ -34,6 +34,8 @@ The server accepts a state and a map of typed questions:
 - `choice`: categorical decision and full probability distribution
 - `score`: expected ordinal score and full probability distribution
 The serving layer performs deterministic single-token candidate readout, forward and reverse option-order evaluation, probability calibration, and schema conversion. The serving layer is part of the released inference configuration and must be used for reproducible results
 ## Quick start
@@ -41,7 +43,7 @@ The serving layer performs deterministic single-token candidate readout, forward
 The following commands download the validated release, verify and extract the serving bundle, and start JevOne on two GPUs:
 ```bash
-export JEVONE_REVISION=4de0db772d718134bd32fe5d4c8da77d97a36240
 export INSTALL_ROOT="$PWD/jev-one-eval"
 export MODEL_DIR="$INSTALL_ROOT/model"
@@ -74,6 +76,14 @@ Test it with the included request:
 curl -sS -X POST http://127.0.0.1:49001/v1/systemone   -H 'Content-Type: application/json'   --data @examples/request.json
 ```
 ## Public JEVBench self-run
 JevOne was evaluated locally on the public tiers of [JEVBench](https://github.com/fstandhartinger/jevbench) using harness commit `fd51755eb0c0b546ca206d764faf3302feca913e`, the existing `typesafe` adapter, and one request at a time

 - `choice`: categorical decision and full probability distribution
 - `score`: expected ordinal score and full probability distribution
+Requests may also include an `images` array containing up to eight image URLs or data URLs. Typed questions can classify information from the supplied images and text
 The serving layer performs deterministic single-token candidate readout, forward and reverse option-order evaluation, probability calibration, and schema conversion. The serving layer is part of the released inference configuration and must be used for reproducible results
 ## Quick start
 The following commands download the validated release, verify and extract the serving bundle, and start JevOne on two GPUs:
 ```bash
+export JEVONE_REVISION=be424564b25db74295ab23ba3e6f03a7dca31567
 export INSTALL_ROOT="$PWD/jev-one-eval"
 export MODEL_DIR="$INSTALL_ROOT/model"
 curl -sS -X POST http://127.0.0.1:49001/v1/systemone   -H 'Content-Type: application/json'   --data @examples/request.json
 ```
+Test image input with the included data-URL request:
+```bash
+curl -sS -X POST http://127.0.0.1:49001/v1/systemone \
+  -H 'Content-Type: application/json' \
+  --data @examples/image-request.json
+```
 ## Public JEVBench self-run
 JevOne was evaluated locally on the public tiers of [JEVBench](https://github.com/fstandhartinger/jevbench) using harness commit `fd51755eb0c0b546ca206d764faf3302feca913e`, the existing `typesafe` adapter, and one request at a time