Instructions to use unicamp-dl/monoptt5-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unicamp-dl/monoptt5-small with Transformers:

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

pipe = pipeline("text-generation", model="unicamp-dl/monoptt5-small")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("unicamp-dl/monoptt5-small")
model = AutoModelForSeq2SeqLM.from_pretrained("unicamp-dl/monoptt5-small", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use unicamp-dl/monoptt5-small with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unicamp-dl/monoptt5-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/monoptt5-small",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/unicamp-dl/monoptt5-small

SGLang

How to use unicamp-dl/monoptt5-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/monoptt5-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/monoptt5-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/monoptt5-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/monoptt5-small",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use unicamp-dl/monoptt5-small with Docker Model Runner:
```
docker model run hf.co/unicamp-dl/monoptt5-small
```

marcospiau commited on Jul 10

Commit

fd93de3

verified ·

1 Parent(s): e5e8bdf

Fix arXiv link for ptt5-v2 paper reference (2008.09144 -> 2406.10806)

Browse files

The introduction links the paper title 'ptt5-v2: A Closer Look at Continued Pretraining of T5 Models for the Portuguese Language' to arXiv 2008.09144, which is the original PTT5 paper. This points it to the correct ptt5-v2 paper (arXiv 2406.10806), matching the eprint already used in the citation block.

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -10,7 +10,7 @@ license: apache-2.0
 ## Introduction
 MonoPTT5 models are T5 rerankers for the Portuguese language. Starting from [ptt5-v2 checkpoints](https://huggingface.co/collections/unicamp-dl/ptt5-v2-666538a650188ba00aa8d2d0), they were trained for 100k steps on a mixture of Portuguese and English data from the mMARCO dataset.
-For further information on the training and evaluation of these models, please refer to our paper, [ptt5-v2: A Closer Look at Continued Pretraining of T5 Models for the Portuguese Language](https://arxiv.org/abs/2008.09144).
 ## Usage
 The easiest way to use our models is through the `rerankers` package. After installing the package using `pip install rerankers[transformers]`, the following code can be used as a minimal working example:

 ## Introduction
 MonoPTT5 models are T5 rerankers for the Portuguese language. Starting from [ptt5-v2 checkpoints](https://huggingface.co/collections/unicamp-dl/ptt5-v2-666538a650188ba00aa8d2d0), they were trained for 100k steps on a mixture of Portuguese and English data from the mMARCO dataset.
+For further information on the training and evaluation of these models, please refer to our paper, [ptt5-v2: A Closer Look at Continued Pretraining of T5 Models for the Portuguese Language](https://arxiv.org/abs/2406.10806).
 ## Usage
 The easiest way to use our models is through the `rerankers` package. After installing the package using `pip install rerankers[transformers]`, the following code can be used as a minimal working example: