Instructions to use DeepBrainz/DeepBrainz-R1-0.6B-40K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DeepBrainz/DeepBrainz-R1-0.6B-40K with Transformers:

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

pipe = pipeline("text-generation", model="DeepBrainz/DeepBrainz-R1-0.6B-40K")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DeepBrainz/DeepBrainz-R1-0.6B-40K")
model = AutoModelForCausalLM.from_pretrained("DeepBrainz/DeepBrainz-R1-0.6B-40K")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DeepBrainz/DeepBrainz-R1-0.6B-40K with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DeepBrainz/DeepBrainz-R1-0.6B-40K"
# 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-R1-0.6B-40K",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DeepBrainz/DeepBrainz-R1-0.6B-40K

SGLang

How to use DeepBrainz/DeepBrainz-R1-0.6B-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-R1-0.6B-40K" \
    --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-R1-0.6B-40K",
		"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-R1-0.6B-40K" \
        --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-R1-0.6B-40K",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DeepBrainz/DeepBrainz-R1-0.6B-40K with Docker Model Runner:
```
docker model run hf.co/DeepBrainz/DeepBrainz-R1-0.6B-40K
```

ArunkumarVR commited on Feb 5

Commit

d524b4a

verified ·

1 Parent(s): ab82498

Update README.md

Browse files

Files changed (1) hide show

README.md +11 -2

README.md CHANGED Viewed

@@ -24,7 +24,7 @@ This model is part of the **DeepBrainz-R1 Series**, built to deliver frontier-cl
 ## 🚀 Model Highlights
 - **Parameter Count:** ~0.6B
-- **Context Window:** 40,960 tokens
 - **Specialization:** STEM Reasoning, Logic, Code Analysis
 - **Architecture:** Optimized Dense Transformer (Qwen2.5/3 Compatible)
 - **Deployment:** Ready for vLLM, TGI, and local inference
@@ -38,7 +38,8 @@ This model is part of the **DeepBrainz-R1 Series**, built to deliver frontier-cl
 - **Code Generation:** Writing and debugging algorithms.
 - **Structured Data Extraction:** Parsing and reasoning over unstructured text.
-> **Note:** This is a base reasoning model. For conversational chat, we recommend using a specific instruct template or fine-tuning on your domain data.
 ---
@@ -65,6 +66,14 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 ---
 ## 🛡️ Limitations & Safety
 While this model demonstrates strong reasoning capabilities, it may still produce inaccurate information ("hallucinations"). Users should implement appropriate guardrails for production deployments.

 ## 🚀 Model Highlights
 - **Parameter Count:** ~0.6B
+- **Context Window:** up to 40,960 tokens (extended context; experimental)
 - **Specialization:** STEM Reasoning, Logic, Code Analysis
 - **Architecture:** Optimized Dense Transformer (Qwen2.5/3 Compatible)
 - **Deployment:** Ready for vLLM, TGI, and local inference
 - **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.
 ---
 ---
+🏗️ Technical Summary
+This model has undergone post-training to enhance reasoning behavior and robustness under agentic workloads.
+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.