Instructions to use monsoon-nlp/es-seq2seq-gender-decoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use monsoon-nlp/es-seq2seq-gender-decoder with Transformers:

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

pipe = pipeline("text-generation", model="monsoon-nlp/es-seq2seq-gender-decoder")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("monsoon-nlp/es-seq2seq-gender-decoder")
model = AutoModelForCausalLM.from_pretrained("monsoon-nlp/es-seq2seq-gender-decoder")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use monsoon-nlp/es-seq2seq-gender-decoder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "monsoon-nlp/es-seq2seq-gender-decoder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "monsoon-nlp/es-seq2seq-gender-decoder",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/monsoon-nlp/es-seq2seq-gender-decoder

SGLang

How to use monsoon-nlp/es-seq2seq-gender-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 "monsoon-nlp/es-seq2seq-gender-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": "monsoon-nlp/es-seq2seq-gender-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 "monsoon-nlp/es-seq2seq-gender-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": "monsoon-nlp/es-seq2seq-gender-decoder",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use monsoon-nlp/es-seq2seq-gender-decoder with Docker Model Runner:
```
docker model run hf.co/monsoon-nlp/es-seq2seq-gender-decoder
```

es-seq2seq-gender (decoder)

This is a seq2seq model (decoder half) to "flip" gender in Spanish sentences. The model can augment your existing Spanish data, or generate counterfactuals to test a model's decisions (would changing the gender of the subject or speaker change output?).

Intended Examples:

el profesor viejo => la profesora vieja (article, noun, adjective all flip)
una actriz => un actor (irregular noun)
el lingüista => la lingüista (irregular noun)
la biblioteca => la biblioteca (no person, no flip)

People's names are unchanged in this version, but you can use packages such as https://pypi.org/project/gender-guesser/

Sample code

https://colab.research.google.com/drive/1Ta_YkXx93FyxqEu_zJ-W23PjPumMNHe5

import torch
from transformers import AutoTokenizer, EncoderDecoderModel

model = EncoderDecoderModel.from_encoder_decoder_pretrained("monsoon-nlp/es-seq2seq-gender-encoder", "monsoon-nlp/es-seq2seq-gender-decoder")
tokenizer = AutoTokenizer.from_pretrained('monsoon-nlp/es-seq2seq-gender-decoder') # all are same as BETO uncased original

input_ids = torch.tensor(tokenizer.encode("la profesora vieja")).unsqueeze(0)
generated = model.generate(input_ids, decoder_start_token_id=model.config.decoder.pad_token_id)
tokenizer.decode(generated.tolist()[0])
> '[PAD] el profesor viejo profesor viejo profesor...'

Training

I originally developed a gender flip Python script with BETO, the Spanish-language BERT from Universidad de Chile, and spaCy to parse dependencies in sentences.

More about this project: https://medium.com/ai-in-plain-english/gender-bias-in-spanish-bert-1f4d76780617

The seq2seq model is trained on gender-flipped text from that script run on the muchocine dataset, and the first 6,853 lines from the OSCAR corpus (Spanish ded-duped).

The encoder and decoder started with weights and vocabulary from BETO (uncased).

Non-binary gender

This model is useful to generate male and female text samples, but falls short of capturing gender diversity in the world and in the Spanish language. Some communities prefer the plural -@s to represent -os and -as, or -e and -es for gender-neutral or mixed-gender plural, or use fewer gendered professional nouns (la juez and not jueza). This is not yet embraced by the Royal Spanish Academy and is not represented in the corpora and tokenizers used to build this project.

This seq2seq project and script could, in the future, help generate more text samples and prepare NLP models to understand us all better.

Sources

Downloads last month: 46