Instructions to use unicamp-dl/ptt5-v2-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unicamp-dl/ptt5-v2-small with Transformers:

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

pipe = pipeline("text-generation", model="unicamp-dl/ptt5-v2-small")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("unicamp-dl/ptt5-v2-small")
model = AutoModelForSeq2SeqLM.from_pretrained("unicamp-dl/ptt5-v2-small", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use unicamp-dl/ptt5-v2-small with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unicamp-dl/ptt5-v2-small"
# 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-v2-small",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/unicamp-dl/ptt5-v2-small

SGLang

How to use unicamp-dl/ptt5-v2-small 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-v2-small" \
    --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-v2-small",
		"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-v2-small" \
        --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-v2-small",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use unicamp-dl/ptt5-v2-small with Docker Model Runner:
```
docker model run hf.co/unicamp-dl/ptt5-v2-small
```

YAML Metadata Warning:The pipeline tag "text2text-generation" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other

ptt5-v2-small

Introduction

ptt5-v2 models are pretrained T5 models tailored for the Portuguese language, continuing from Google's original checkpoints with sizes from t5-small to t5-3B. These checkpoints were used to train MonoT5 rerankers for the Portuguese language, which can be found in their HuggingFace collection. For further information about the pretraining process, please refer to our paper, ptt5-v2: A Closer Look at Continued Pretraining of T5 Models for the Portuguese Language.

Usage

from transformers import T5Tokenizer, T5ForConditionalGeneration

tokenizer = T5Tokenizer.from_pretrained("unicamp-dl/ptt5-v2-small")
model = T5ForConditionalGeneration.from_pretrained("unicamp-dl/ptt5-v2-small")

Citation

If you use our models, please cite:

@misc{piau2024ptt5v2,
      title={ptt5-v2: A Closer Look at Continued Pretraining of T5 Models for the Portuguese Language}, 
      author={Marcos Piau and Roberto Lotufo and Rodrigo Nogueira},
      year={2024},
      eprint={2406.10806},
      archivePrefix={arXiv},
      primaryClass={id='cs.CL' full_name='Computation and Language' is_active=True alt_name='cmp-lg' in_archive='cs' is_general=False description='Covers natural language processing. Roughly includes material in ACM Subject Class I.2.7. Note that work on artificial languages (programming languages, logics, formal systems) that does not explicitly address natural-language issues broadly construed (natural-language processing, computational linguistics, speech, text retrieval, etc.) is not appropriate for this area.'}
}