Instructions to use DeepBrainz/DeepBrainz-R1-4B-40K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DeepBrainz/DeepBrainz-R1-4B-40K with Transformers:

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

pipe = pipeline("text-generation", model="DeepBrainz/DeepBrainz-R1-4B-40K")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DeepBrainz/DeepBrainz-R1-4B-40K")
model = AutoModelForCausalLM.from_pretrained("DeepBrainz/DeepBrainz-R1-4B-40K")
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 DeepBrainz/DeepBrainz-R1-4B-40K with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DeepBrainz/DeepBrainz-R1-4B-40K"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeepBrainz/DeepBrainz-R1-4B-40K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DeepBrainz/DeepBrainz-R1-4B-40K

SGLang

How to use DeepBrainz/DeepBrainz-R1-4B-40K 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 "DeepBrainz/DeepBrainz-R1-4B-40K" \
    --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": "DeepBrainz/DeepBrainz-R1-4B-40K",
		"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 "DeepBrainz/DeepBrainz-R1-4B-40K" \
        --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": "DeepBrainz/DeepBrainz-R1-4B-40K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DeepBrainz/DeepBrainz-R1-4B-40K with Docker Model Runner:
```
docker model run hf.co/DeepBrainz/DeepBrainz-R1-4B-40K
```

DeepBrainz-R1-4B-40K

DeepBrainz-R1-4B-40K is a compact, high-performance reasoning model engineered by DeepBrainz AI & Labs. It is part of the DeepBrainz-R1 Series, designed to deliver frontier-class reasoning capabilities in cost-effective parameter sizes.

This specific variant offers a 40,960 token context window, making it suitable for extended-context evaluation and repository-level code reasoning.

🚀 Model Highlights

Parameter Count: ~4B
Context Window: up to 40,960 tokens (extended context; experimental)
Context Type: Extended (RoPE)
Specialization: STEM Reasoning, Logic, Code Analysis
Architecture: Optimized Dense Transformer
Deployment: Ready for vLLM, TGI, and local inference

🎯 Intended Use Cases

Agentic Workflows: Reliability in multi-step planning tasks.
Math & Science: Solving complex word problems and equations.
Code Generation: Writing and debugging algorithms.
Structured Data Extraction: Parsing and reasoning over unstructured text.

Note: This is a post-trained reasoning variant intended for evaluation and experimentation.
It is not production-validated and is not optimized for open-ended conversational chat.

💻 Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "DeepBrainz/DeepBrainz-R1-4B-40K"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="bfloat16",
    device_map="auto"
)

prompt = "Analyze the time complexity of the following algorithm:"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

🏗️ Technical Summary

This model has undergone post-training to improve structured reasoning behavior, mathematical problem solving, and robustness in agentic workflows.

Detailed post-training recipes and dataset compositions are not fully disclosed.

🛡️ Limitations & Safety

While this model demonstrates strong reasoning capabilities, it may still produce inaccurate information ("hallucinations"). Users should implement appropriate guardrails for production deployments.

📜 License

This model is released under the Apache 2.0 license, allowing for academic and commercial use.

DeepBrainz AI & Labs
Advancing General Intelligence through Scalable Reasoning

Downloads last month: 7

Collection including DeepBrainz/DeepBrainz-R1-4B-40K

DeepBrainz-R1 — Reasoning-First SLMs for Agentic Systems

Collection

Reasoning-first Small Language Models for agentic AI systems in production. • 13 items • Updated Feb 4 • 1