Instructions to use deca-ai/2-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deca-ai/2-mini with Transformers:

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

pipe = pipeline("text-generation", model="deca-ai/2-mini")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deca-ai/2-mini")
model = AutoModelForCausalLM.from_pretrained("deca-ai/2-mini")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use deca-ai/2-mini with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deca-ai/2-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": "deca-ai/2-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deca-ai/2-mini

SGLang

How to use deca-ai/2-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 "deca-ai/2-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": "deca-ai/2-mini",
		"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 "deca-ai/2-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": "deca-ai/2-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deca-ai/2-mini with Docker Model Runner:
```
docker model run hf.co/deca-ai/2-mini
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

The Deca 2 family of models, now generally availible, is built on cutting-edge architectures like DeepSeek R1, LLaMA 3, and Qwen 2, delivering extraordinary performance. With a focus on insane speed and high efficiency, Deca 2 is revolutionizing text generation and setting new standards in the industry. It also comes with a 1 million context window.

As more capabilities are added, Deca 2 will evolve into a more powerful, any-to-any model in the future. While it’s focused on text generation for now, its foundation is designed to scale, bringing even more advanced functionalities to come.

3/3 Release

Updated weights with better experts
Made Deca 2 Mini Generally Availible 2/14 Release:
Enhanced Instruction Following

Downloads last month: 9

Safetensors

Model size

15B params

Tensor type

BF16

Model tree for deca-ai/2-mini

Base model

deepseek-ai/DeepSeek-R1

Finetuned

(321)

this model

Quantizations

3 models

deca-ai
/

2-mini

Model tree for deca-ai/2-mini

Space using deca-ai/2-mini 1