Text Generation
Transformers
Safetensors
English
qwen3
deepbrainz
reasoning
mathematics
code
enterprise
2b
conversational
text-generation-inference
Instructions to use DeepBrainz/DeepBrainz-R1-2B-16K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DeepBrainz/DeepBrainz-R1-2B-16K with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="DeepBrainz/DeepBrainz-R1-2B-16K") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("DeepBrainz/DeepBrainz-R1-2B-16K") model = AutoModelForCausalLM.from_pretrained("DeepBrainz/DeepBrainz-R1-2B-16K", device_map="auto") 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=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use DeepBrainz/DeepBrainz-R1-2B-16K 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-16K" # 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-R1-2B-16K", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/DeepBrainz/DeepBrainz-R1-2B-16K
- SGLang
How to use DeepBrainz/DeepBrainz-R1-2B-16K 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-16K" \ --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-R1-2B-16K", "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-R1-2B-16K" \ --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-R1-2B-16K", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use DeepBrainz/DeepBrainz-R1-2B-16K with Docker Model Runner:
docker model run hf.co/DeepBrainz/DeepBrainz-R1-2B-16K
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,9 +10,9 @@ tags:
|
|
| 10 |
- research
|
| 11 |
---
|
| 12 |
|
| 13 |
-
# DeepBrainz-R1
|
| 14 |
|
| 15 |
-
**DeepBrainz-R1
|
| 16 |
DeepBrainz-R series, designed for structured problem-solving, analysis,
|
| 17 |
and enterprise research workflows.
|
| 18 |
|
|
@@ -47,7 +47,7 @@ Not intended as a general-purpose chat replacement for large frontier models.
|
|
| 47 |
```python
|
| 48 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 49 |
|
| 50 |
-
model_id = "DeepBrainz/DeepBrainz-R1
|
| 51 |
|
| 52 |
tok = AutoTokenizer.from_pretrained(model_id)
|
| 53 |
mdl = AutoModelForCausalLM.from_pretrained(model_id)
|
|
@@ -58,6 +58,7 @@ inputs = tok(prompt, return_tensors="pt")
|
|
| 58 |
out = mdl.generate(
|
| 59 |
**inputs,
|
| 60 |
max_new_tokens=256,
|
|
|
|
| 61 |
temperature=0.6,
|
| 62 |
top_p=0.95,
|
| 63 |
)
|
|
@@ -79,7 +80,7 @@ abstracted in this public release.
|
|
| 79 |
## Limitations
|
| 80 |
|
| 81 |
Performance depends on task complexity and inference configuration.
|
| 82 |
-
Larger models may outperform R1
|
| 83 |
|
| 84 |
---
|
| 85 |
|
|
|
|
| 10 |
- research
|
| 11 |
---
|
| 12 |
|
| 13 |
+
# DeepBrainz-R1-2B-16K
|
| 14 |
|
| 15 |
+
**DeepBrainz-R1-2B-16K** is a compact, long-context reasoning model in the
|
| 16 |
DeepBrainz-R series, designed for structured problem-solving, analysis,
|
| 17 |
and enterprise research workflows.
|
| 18 |
|
|
|
|
| 47 |
```python
|
| 48 |
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 49 |
|
| 50 |
+
model_id = "DeepBrainz/DeepBrainz-R1-2B-16K"
|
| 51 |
|
| 52 |
tok = AutoTokenizer.from_pretrained(model_id)
|
| 53 |
mdl = AutoModelForCausalLM.from_pretrained(model_id)
|
|
|
|
| 58 |
out = mdl.generate(
|
| 59 |
**inputs,
|
| 60 |
max_new_tokens=256,
|
| 61 |
+
do_sample=True,
|
| 62 |
temperature=0.6,
|
| 63 |
top_p=0.95,
|
| 64 |
)
|
|
|
|
| 80 |
## Limitations
|
| 81 |
|
| 82 |
Performance depends on task complexity and inference configuration.
|
| 83 |
+
Larger models may outperform R1-2B-16K on extremely complex tasks.
|
| 84 |
|
| 85 |
---
|
| 86 |
|