Instructions to use Polygl0t/Tucano2-qwen-3.7B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Polygl0t/Tucano2-qwen-3.7B-Base with Transformers:

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

pipe = pipeline("text-generation", model="Polygl0t/Tucano2-qwen-3.7B-Base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Polygl0t/Tucano2-qwen-3.7B-Base")
model = AutoModelForCausalLM.from_pretrained("Polygl0t/Tucano2-qwen-3.7B-Base")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Polygl0t/Tucano2-qwen-3.7B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Polygl0t/Tucano2-qwen-3.7B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Polygl0t/Tucano2-qwen-3.7B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Polygl0t/Tucano2-qwen-3.7B-Base

SGLang

How to use Polygl0t/Tucano2-qwen-3.7B-Base 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 "Polygl0t/Tucano2-qwen-3.7B-Base" \
    --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": "Polygl0t/Tucano2-qwen-3.7B-Base",
		"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 "Polygl0t/Tucano2-qwen-3.7B-Base" \
        --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": "Polygl0t/Tucano2-qwen-3.7B-Base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Polygl0t/Tucano2-qwen-3.7B-Base with Docker Model Runner:
```
docker model run hf.co/Polygl0t/Tucano2-qwen-3.7B-Base
```

nicholasKluge commited on Mar 5

Commit

1bebfaf

verified ·

1 Parent(s): 788a16b

Update README.md

Browse files

Files changed (1) hide show

README.md +9 -1

README.md CHANGED Viewed

@@ -473,7 +473,15 @@ This plot compares the compute requirements (measured as C = 6 \* N \* D, where
 ## Cite as 🤗
 ```latex
 ```
 ## Aknowlegments

 ## Cite as 🤗
 ```latex
+@misc{correa2026tucano2cool,
+      title={{Tucano 2 Cool: Better Open Source LLMs for Portuguese}},
+      author={Nicholas Kluge Corr{\^e}a and Aniket Sen and Shiza Fatimah and Sophia Falk and Lennard Landgraf and Julia Kastner and Lucie Flek},
+      year={2026},
+      eprint={2603.03543},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2603.03543},
+}
 ```
 ## Aknowlegments