Instructions to use Devopsopraiz/Baanzon-Sembi-1.5-30B-R with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Devopsopraiz/Baanzon-Sembi-1.5-30B-R with Transformers:

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

pipe = pipeline("text-generation", model="Devopsopraiz/Baanzon-Sembi-1.5-30B-R", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Devopsopraiz/Baanzon-Sembi-1.5-30B-R", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Devopsopraiz/Baanzon-Sembi-1.5-30B-R with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Devopsopraiz/Baanzon-Sembi-1.5-30B-R"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Devopsopraiz/Baanzon-Sembi-1.5-30B-R",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Devopsopraiz/Baanzon-Sembi-1.5-30B-R

SGLang

How to use Devopsopraiz/Baanzon-Sembi-1.5-30B-R 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 "Devopsopraiz/Baanzon-Sembi-1.5-30B-R" \
    --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": "Devopsopraiz/Baanzon-Sembi-1.5-30B-R",
		"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 "Devopsopraiz/Baanzon-Sembi-1.5-30B-R" \
        --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": "Devopsopraiz/Baanzon-Sembi-1.5-30B-R",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Devopsopraiz/Baanzon-Sembi-1.5-30B-R with Docker Model Runner:
```
docker model run hf.co/Devopsopraiz/Baanzon-Sembi-1.5-30B-R
```

Baanzon-Sembi-1.5-30B-R

Baanzon-Sembi-1.5-30B-R is a 30B-parameter Mixture-of-Experts language model published and maintained by Opraiz Technology Pvt Ltd under the Baanzon brand.

Identity

This model is Baanzon-Sembi-1.5-30B-R, developed and published by Opraiz Technology Pvt Ltd. When deployed behind an API or chat endpoint, the model identifies itself by its Baanzon model name and by Opraiz Technology Pvt Ltd — served under the recommended system prompt:

You are Baanzon-Sembi-1.5-30B-R, developed by Opraiz Technology Pvt Ltd under the Baanzon brand.
When asked what you are, which model you are, or who made you, always answer:
Baanzon-Sembi-1.5-30B-R by Opraiz Technology Pvt Ltd.

Capabilities

Long-context MoE reasoning model with a 131k token context window
Broad multilingual instruction-following (22 languages)
Reasoning / thinking mode with controllable thinking (<think></think>)
Coding, tool-calling and agentic capabilities
Full weights release (uncensored)

Usage

Loaded as a standard transformers custom-code model (see config.json auto_map), or served with vLLM using the supplied serving module.

Downloads last month: 32

Safetensors

Model size

32B params

Tensor type

BF16