Instructions to use James7765/WilR-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use James7765/WilR-mini with Transformers:

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

pipe = pipeline("image-text-to-text", model="James7765/WilR-mini")
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("James7765/WilR-mini")
model = AutoModelForMultimodalLM.from_pretrained("James7765/WilR-mini", 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 James7765/WilR-mini with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "James7765/WilR-mini"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "James7765/WilR-mini",
		"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/James7765/WilR-mini

SGLang

How to use James7765/WilR-mini 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 "James7765/WilR-mini" \
    --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": "James7765/WilR-mini",
		"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 "James7765/WilR-mini" \
        --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": "James7765/WilR-mini",
		"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 James7765/WilR-mini with Docker Model Runner:
```
docker model run hf.co/James7765/WilR-mini
```

WilR-mini / README.md

James7765

Update README.md

f158f32 verified 11 months ago

preview code

Raw

History Blame Contribute Delete

1.54 kB

	---
	base_model:
	- James7765/WilR_9
	tags:
	- text-generation-inference
	- transformers
	license: apache-2.0
	language:
	- en
	---

	# new ai model

	- Developed by: James7765
	- License: apache-2.0
	- by Spectra.inc LTD jamaica


	🚀 Introducing WilR-mini: Smart, Fast, and Compact 🤖

	Meet WilR-mini, the minified version of our powerful AI model WilR-9 💻. WilR-mini is designed to deliver the same level of intelligence and accuracy as its larger counterpart, but with a smaller footprint and faster performance ⚡️.

	Key Features:

	- 2.4X Faster ⏱️: WilR-mini is optimized for speed, making it perfect for applications where every millisecond counts.
	- Smart and Accurate 🤔: Despite its compact size, WilR-mini retains the intelligence and accuracy of WilR-9, ensuring you get reliable results.
	- Minified for Efficiency 💸: WilR-mini is carefully optimized to reduce computational requirements, making it ideal for deployment on resource-constrained devices or in environments where efficiency is crucial.

	Use WilR-mini for:

	- Real-time text generation and processing 📝
	- Conversational AI and chatbots 💬
	- Sentiment analysis and opinion mining 💡
	- Language translation and more 🌎
	- - its the first Ai ever to be made in the carribean (jamaican product)

	Experience the power of WilR-9 in a compact package. Try WilR-mini today! 🚀
	[<img src="https://raw.githubusercontent.com/Wisk-inc/wisk.githujsjs/refs/heads/main/sparkles.png" width="200"/>](https://github.com/unslothai/unsloth)