Instructions to use DeepBrainz/DeepBrainz-R1-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DeepBrainz/DeepBrainz-R1-2B with Transformers:

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

pipe = pipeline("text-generation", model="DeepBrainz/DeepBrainz-R1-2B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DeepBrainz/DeepBrainz-R1-2B")
model = AutoModelForCausalLM.from_pretrained("DeepBrainz/DeepBrainz-R1-2B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DeepBrainz/DeepBrainz-R1-2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DeepBrainz/DeepBrainz-R1-2B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeepBrainz/DeepBrainz-R1-2B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DeepBrainz/DeepBrainz-R1-2B

SGLang

How to use DeepBrainz/DeepBrainz-R1-2B 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-R1-2B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeepBrainz/DeepBrainz-R1-2B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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-R1-2B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeepBrainz/DeepBrainz-R1-2B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DeepBrainz/DeepBrainz-R1-2B with Docker Model Runner:
```
docker model run hf.co/DeepBrainz/DeepBrainz-R1-2B
```

ArunkumarVR commited on Feb 3

Commit

4f34492

verified ·

1 Parent(s): 3468263

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -4

README.md CHANGED Viewed

@@ -11,13 +11,12 @@ tags:
   - enterprise
   - 2b
   - long-context
-base_model: Qwen/Qwen3-2B
 library_name: transformers
 ---
-# DeepBrainz-R1-2B-32K
-**DeepBrainz-R1-2B-32K** 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 variant features a **32,768 token context window**, optimized for processing medium-to-long documents and codebases.
@@ -49,7 +48,7 @@ This variant features a **32,768 token context window**, optimized for processin
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
-model_id = "DeepBrainz/DeepBrainz-R1-2B-32K"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(

   - enterprise
   - 2b
   - long-context
 library_name: transformers
 ---
+# DeepBrainz-R1-2B
+**DeepBrainz-R1-2B** 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 variant features a **32,768 token context window**, optimized for processing medium-to-long documents and codebases.
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
+model_id = "DeepBrainz/DeepBrainz-R1-2B"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(