Instructions to use TucanoBR/Tucano-2b4-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TucanoBR/Tucano-2b4-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="TucanoBR/Tucano-2b4-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TucanoBR/Tucano-2b4-Instruct")
model = AutoModelForCausalLM.from_pretrained("TucanoBR/Tucano-2b4-Instruct", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TucanoBR/Tucano-2b4-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TucanoBR/Tucano-2b4-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TucanoBR/Tucano-2b4-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TucanoBR/Tucano-2b4-Instruct

SGLang

How to use TucanoBR/Tucano-2b4-Instruct 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 "TucanoBR/Tucano-2b4-Instruct" \
    --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": "TucanoBR/Tucano-2b4-Instruct",
		"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 "TucanoBR/Tucano-2b4-Instruct" \
        --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": "TucanoBR/Tucano-2b4-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TucanoBR/Tucano-2b4-Instruct with Docker Model Runner:
```
docker model run hf.co/TucanoBR/Tucano-2b4-Instruct
```

Tucano-2b4-Instruct / EVALS-2b4-instruct.csv

nicholasKluge

Upload EVALS-2b4-instruct.csv with huggingface_hub

34f3970 verified almost 2 years ago

Raw

History Blame Contribute Delete

357 Bytes

	model,average,calame_pt,lambada_pt,enem,bluex,oab_exams,assin2_rte,assin2_sts,faquad_nli,hatebr,hatespeech_pt,tweet_br,arc_pt,hellaswag_pt,truthfulqa
	Tucano-2b4-sft,33.26,58.24,37.36,20.92,20.58,25.97,33.33,7.79,43.97,43.05,35.90,21.15,30.85,47.51,39.07
	Tucano-2b4-dpo,34.14,57.66,39.92,20.43,22.81,24.83,43.39,6.31,43.97,27.70,29.18,43.11,32.05,48.28,38.44