Instructions to use limajr/NBR-1B-Portuguese-MCQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use limajr/NBR-1B-Portuguese-MCQ with Transformers:

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

pipe = pipeline("text-generation", model="limajr/NBR-1B-Portuguese-MCQ")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("limajr/NBR-1B-Portuguese-MCQ")
model = AutoModelForCausalLM.from_pretrained("limajr/NBR-1B-Portuguese-MCQ")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use limajr/NBR-1B-Portuguese-MCQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "limajr/NBR-1B-Portuguese-MCQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "limajr/NBR-1B-Portuguese-MCQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/limajr/NBR-1B-Portuguese-MCQ

SGLang

How to use limajr/NBR-1B-Portuguese-MCQ 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 "limajr/NBR-1B-Portuguese-MCQ" \
    --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": "limajr/NBR-1B-Portuguese-MCQ",
		"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 "limajr/NBR-1B-Portuguese-MCQ" \
        --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": "limajr/NBR-1B-Portuguese-MCQ",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use limajr/NBR-1B-Portuguese-MCQ with Docker Model Runner:
```
docker model run hf.co/limajr/NBR-1B-Portuguese-MCQ
```

NBR-1B-Portuguese-MCQ

O melhor modelo ~1B parametros para questoes de multipla escolha em Portugues.

Highlights

#1 em ENEM (30.53%) - Vestibular brasileiro
#1 em OAB (49.70%) - Exame da Ordem dos Advogados
#1 em BLUEX (36.54%) - Vestibulares universitarios
#1 em tweetSentBR (39.70%) - Analise de sentimento

Benchmarks

Benchmark	Score	Ranking
ENEM	30.53%	#1
OAB Exams	49.70%	#1
BLUEX	36.54%	#1
TweetSentBR	39.70%	#1
FAQUAD NLI	45.55%	Top 3
HateBR	43.18%	Top 5
PT Hate Speech	41.99%	Top 5
ASSIN2 RTE	34.27%	-
ASSIN2 STS	0.99%	-
Average	35.83%	-

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("limajr/NBR-1B-Portuguese-MCQ")
tokenizer = AutoTokenizer.from_pretrained("limajr/NBR-1B-Portuguese-MCQ")

Model Details

Architecture: LlamaForCausalLM
Parameters: ~1.5B
Hidden Size: 2048
Layers: 24
Attention Heads: 16
Language: Portuguese (pt-BR)
Training: Supervised Fine-Tuning on Brazilian educational content
License: Apache 2.0

Training Data

Fine-tuned on curated Portuguese datasets including:

Brazilian educational materials
Legal texts (OAB preparation)
General knowledge QA

Evaluation

Evaluated on the Open PT LLM Leaderboard using the standard evaluation protocol.

Limitations

Optimized for multiple choice questions
ASSIN2 STS (semantic similarity) performance is limited
Best used for Portuguese educational contexts

Downloads last month: 1

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for limajr/NBR-1B-Portuguese-MCQ

Finetunes

1 model