Instructions to use SZLHOLDINGS/willay-r2-candidate with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SZLHOLDINGS/willay-r2-candidate with Transformers:

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

pipe = pipeline("text-generation", model="SZLHOLDINGS/willay-r2-candidate")
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("SZLHOLDINGS/willay-r2-candidate")
model = AutoModelForMultimodalLM.from_pretrained("SZLHOLDINGS/willay-r2-candidate", 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 SZLHOLDINGS/willay-r2-candidate with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SZLHOLDINGS/willay-r2-candidate"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SZLHOLDINGS/willay-r2-candidate",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SZLHOLDINGS/willay-r2-candidate

SGLang

How to use SZLHOLDINGS/willay-r2-candidate 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 "SZLHOLDINGS/willay-r2-candidate" \
    --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": "SZLHOLDINGS/willay-r2-candidate",
		"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 "SZLHOLDINGS/willay-r2-candidate" \
        --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": "SZLHOLDINGS/willay-r2-candidate",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SZLHOLDINGS/willay-r2-candidate with Docker Model Runner:
```
docker model run hf.co/SZLHOLDINGS/willay-r2-candidate
```

card: add missing Evaluation sections from repo files

by betterwithage - opened 1 day ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+14

-0

betterwithage

SZL Holdings org 1 day ago

Card-only change to README.md. Adds the Evaluation section(s) this card was missing, under a dated "Card completeness" heading appended at the end. Existing text is unchanged.

Every statement comes from files in this repository (configs, receipts, data files) or the estate's own receipt datasets. Where there is no evidence, the card says not yet evaluated / not yet documented.
No metrics are invented; no license, visibility, pin, gating or pricing change; no status flags are set.
Merging rebuilds nothing (this is a model repo, not a Space).

Opened as part of the 2026-11-12 Hugging Face org card audit. Please review before merging.

card: add missing Evaluation sections from repo filescbd76a09

betterwithage changed pull request status to merged 1 day ago

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