Instructions to use unicamp-dl/ptt5-large-t5-vocab with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unicamp-dl/ptt5-large-t5-vocab with Transformers:

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

pipe = pipeline("text-generation", model="unicamp-dl/ptt5-large-t5-vocab")

# Load model directly
from transformers import AutoTokenizer, AutoModelWithLMHead

tokenizer = AutoTokenizer.from_pretrained("unicamp-dl/ptt5-large-t5-vocab")
model = AutoModelWithLMHead.from_pretrained("unicamp-dl/ptt5-large-t5-vocab")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use unicamp-dl/ptt5-large-t5-vocab with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unicamp-dl/ptt5-large-t5-vocab"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unicamp-dl/ptt5-large-t5-vocab",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/unicamp-dl/ptt5-large-t5-vocab

SGLang

How to use unicamp-dl/ptt5-large-t5-vocab 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 "unicamp-dl/ptt5-large-t5-vocab" \
    --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": "unicamp-dl/ptt5-large-t5-vocab",
		"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 "unicamp-dl/ptt5-large-t5-vocab" \
        --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": "unicamp-dl/ptt5-large-t5-vocab",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use unicamp-dl/ptt5-large-t5-vocab with Docker Model Runner:
```
docker model run hf.co/unicamp-dl/ptt5-large-t5-vocab
```

Portuguese T5 (aka "PTT5")

Introduction

PTT5 is a T5 model pretrained in the BrWac corpus, a large collection of web pages in Portuguese, improving T5's performance on Portuguese sentence similarity and entailment tasks. It's available in three sizes (small, base and large) and two vocabularies (Google's T5 original and ours, trained on Portuguese Wikipedia).

For further information or requests, please go to PTT5 repository.

Available models

Model	Size	#Params	Vocabulary
unicamp-dl/ptt5-small-t5-vocab	small	60M	Google's T5
unicamp-dl/ptt5-base-t5-vocab	base	220M	Google's T5
unicamp-dl/ptt5-large-t5-vocab	large	740M	Google's T5
unicamp-dl/ptt5-small-portuguese-vocab	small	60M	Portuguese
unicamp-dl/ptt5-base-portuguese-vocab (Recommended)	base	220M	Portuguese
unicamp-dl/ptt5-large-portuguese-vocab	large	740M	Portuguese

Usage

# Tokenizer 
from transformers import T5Tokenizer

# PyTorch (bare model, baremodel + language modeling head)
from transformers import T5Model, T5ForConditionalGeneration

# Tensorflow (bare model, baremodel + language modeling head)
from transformers import TFT5Model, TFT5ForConditionalGeneration

model_name = 'unicamp-dl/ptt5-base-portuguese-vocab'

tokenizer = T5Tokenizer.from_pretrained(model_name)

# PyTorch
model_pt = T5ForConditionalGeneration.from_pretrained(model_name)

# TensorFlow
model_tf = TFT5ForConditionalGeneration.from_pretrained(model_name)

Citation

If you use PTT5, please cite:

@article{ptt5_2020,
  title={PTT5: Pretraining and validating the T5 model on Brazilian Portuguese data},
  author={Carmo, Diedre and Piau, Marcos and Campiotti, Israel and Nogueira, Rodrigo and Lotufo, Roberto},
  journal={arXiv preprint arXiv:2008.09144},
  year={2020}
}

Downloads last month: 18

Model tree for unicamp-dl/ptt5-large-t5-vocab

Finetunes

4 models

Collection including unicamp-dl/ptt5-large-t5-vocab

PTT5

Collection

7 items • Updated Jun 16, 2024

Paper for unicamp-dl/ptt5-large-t5-vocab

PTT5: Pretraining and validating the T5 model on Brazilian Portuguese data

Paper • 2008.09144 • Published Aug 20, 2020