Instructions to use PORTULAN/gervasio-7b-portuguese-ptbr-decoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PORTULAN/gervasio-7b-portuguese-ptbr-decoder with Transformers:

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

pipe = pipeline("text-generation", model="PORTULAN/gervasio-7b-portuguese-ptbr-decoder")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PORTULAN/gervasio-7b-portuguese-ptbr-decoder")
model = AutoModelForCausalLM.from_pretrained("PORTULAN/gervasio-7b-portuguese-ptbr-decoder")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use PORTULAN/gervasio-7b-portuguese-ptbr-decoder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PORTULAN/gervasio-7b-portuguese-ptbr-decoder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PORTULAN/gervasio-7b-portuguese-ptbr-decoder",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/PORTULAN/gervasio-7b-portuguese-ptbr-decoder

SGLang

How to use PORTULAN/gervasio-7b-portuguese-ptbr-decoder 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 "PORTULAN/gervasio-7b-portuguese-ptbr-decoder" \
    --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": "PORTULAN/gervasio-7b-portuguese-ptbr-decoder",
		"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 "PORTULAN/gervasio-7b-portuguese-ptbr-decoder" \
        --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": "PORTULAN/gervasio-7b-portuguese-ptbr-decoder",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use PORTULAN/gervasio-7b-portuguese-ptbr-decoder with Docker Model Runner:
```
docker model run hf.co/PORTULAN/gervasio-7b-portuguese-ptbr-decoder
```

This is the model card for Gervásio 7B PTBR Decoder. You may be interested in some of the other models in the Albertina (encoders), Gervásio (decoders) and Serafim (sentence encoder) families.

Gervásio 7B PTBR

This model has been deprecated.

We recommend you use the improved gervasio-8b-portuguese-ptpt-decoder.

Downloads last month: 10

Safetensors

Model size

7B params

Tensor type

BF16

Datasets used to train PORTULAN/gervasio-7b-portuguese-ptbr-decoder

Spaces using PORTULAN/gervasio-7b-portuguese-ptbr-decoder 17

Paper for PORTULAN/gervasio-7b-portuguese-ptbr-decoder

Advancing Generative AI for Portuguese with Open Decoder Gervásio PT*

Paper • 2402.18766 • Published Feb 29, 2024