Instructions to use soob3123/Veiled-Calla-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use soob3123/Veiled-Calla-12B with Transformers:

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

pipe = pipeline("text-generation", model="soob3123/Veiled-Calla-12B")
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, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("soob3123/Veiled-Calla-12B")
model = AutoModelForImageTextToText.from_pretrained("soob3123/Veiled-Calla-12B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use soob3123/Veiled-Calla-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "soob3123/Veiled-Calla-12B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "soob3123/Veiled-Calla-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/soob3123/Veiled-Calla-12B

SGLang

How to use soob3123/Veiled-Calla-12B 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 "soob3123/Veiled-Calla-12B" \
    --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": "soob3123/Veiled-Calla-12B",
		"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 "soob3123/Veiled-Calla-12B" \
        --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": "soob3123/Veiled-Calla-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use soob3123/Veiled-Calla-12B with Docker Model Runner:
```
docker model run hf.co/soob3123/Veiled-Calla-12B
```

My first impressions

by Emalog - opened Apr 27, 2025

Discussion

Emalog

Apr 27, 2025

I tried this LLM and had a pleasant experience. It reliably maintained character information up to a 16K context size. Its communication, using my character card, is close to Sao10k Lunaris, which is advantageous for me, there are emotions, which is better than many other LLMs. However, since I'm not a native English speaker, it occasionally uses turns of phrase or sentence structures that I don't understand. I haven't tried explicitly intimate scenes with it yet, but flirting is possible, although it does so more reservedly than the aforementioned Lunaris model. This might just be its nature, or perhaps it can be fine-tuned through settings.

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