Instructions to use soob3123/Veiled-Calla-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use soob3123/Veiled-Calla-4B with Transformers:

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

pipe = pipeline("text-generation", model="soob3123/Veiled-Calla-4B")
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("soob3123/Veiled-Calla-4B")
model = AutoModelForMultimodalLM.from_pretrained("soob3123/Veiled-Calla-4B")
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
Local Apps Settings

vLLM

How to use soob3123/Veiled-Calla-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "soob3123/Veiled-Calla-4B"
# 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-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/soob3123/Veiled-Calla-4B

SGLang

How to use soob3123/Veiled-Calla-4B 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-4B" \
    --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-4B",
		"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-4B" \
        --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-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use soob3123/Veiled-Calla-4B with Docker Model Runner:
```
docker model run hf.co/soob3123/Veiled-Calla-4B
```

First RP finetune to pass my inferred reasoning test!

by BingoBird - opened Feb 11

Discussion

BingoBird

Feb 11

Heads up folks! Only 20% of <12B models from 2024-2026 pass my inferred-reasoning test.

This one does! Mradermacher's Q4_K_M quant wins for being the smallest yet that passes!

For reference the winners are:

2.4G gemma-3-4b-Veiled-Calla-4B.i1-Q4_K_M.gguf
2.4G Qwen3-4B-Hivemind-Inst-Hrtic-Ablit-Uncensored-Q4_K_M-imat.gguf
2.4G Qwen3-4B-Instruct-2507-Q4_K_M.gguf
2.7G gemma-3-4b-it-abliterated-normpreserve.i1-Q5_K_M.gguf
2.7G Qwen3-4B-Thinking-2507-Q5_K_M.gguf
2.9G Minitron-4B-Base.i1-Q5_K_M.gguf
3.0G Gemmasutra-4B-v3a-Q6_K.gguf
3.4G Entropy-Qwen3-4B-Base.i1-Q6_K.gguf
4.0G Qwen3-4B-Claude-Sonnet-4-RS-DS-ST.Q8_0.gguf
4.0G Qwen3-4B-Hivemind-Inst-Hrtic-Ablit-Uncensored-Q8_0-imat.gguf
4.0G Qwen3-Instruct-4B-Kepler-186f.Q8_0.gguf
4.5G LFM2-8B-A1B-Q4_K_S.gguf
4.7G Mamba-Codestral-7B-v0.1-Q5_0.gguf
5.8G Apriel-1.6-15b-Thinker.i1-IQ3_XS.gguf
6.2G gemma-3-12b-it-norm-preserved-biprojected-abliterated.i1-IQ4_XS.gguf

Thank you soob3123. I cannot comment on other aspects of the model at this time.

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