Instructions to use SkitCon/gec-spanish-BARTO-COWS-L2H with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SkitCon/gec-spanish-BARTO-COWS-L2H with Transformers:

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

pipe = pipeline("text-generation", model="SkitCon/gec-spanish-BARTO-COWS-L2H")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("SkitCon/gec-spanish-BARTO-COWS-L2H")
model = AutoModelForSeq2SeqLM.from_pretrained("SkitCon/gec-spanish-BARTO-COWS-L2H")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SkitCon/gec-spanish-BARTO-COWS-L2H with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SkitCon/gec-spanish-BARTO-COWS-L2H"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SkitCon/gec-spanish-BARTO-COWS-L2H",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/SkitCon/gec-spanish-BARTO-COWS-L2H

SGLang

How to use SkitCon/gec-spanish-BARTO-COWS-L2H 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 "SkitCon/gec-spanish-BARTO-COWS-L2H" \
    --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": "SkitCon/gec-spanish-BARTO-COWS-L2H",
		"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 "SkitCon/gec-spanish-BARTO-COWS-L2H" \
        --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": "SkitCon/gec-spanish-BARTO-COWS-L2H",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use SkitCon/gec-spanish-BARTO-COWS-L2H with Docker Model Runner:
```
docker model run hf.co/SkitCon/gec-spanish-BARTO-COWS-L2H
```

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

This model has been trained on 80% of the COWS-L2H dataset for grammatical error correction of Spanish text. The corpus was sentencized, so the model has been fine-tuned for SENTENCE CORRECTION. This model will likely not perform well on an entire paragraph. To correct a paragraph, sentencize the text and run the model for each sentence.

BLEU: 0.846 on COWS-L2H

Example usage:

from transformers import AutoTokenizer, BartForConditionalGeneration

tokenizer = AutoTokenizer.from_pretrained("SkitCon/gec-spanish-BARTO-COWS-L2H")
model = BartForConditionalGeneration.from_pretrained("SkitCon/gec-spanish-BARTO-COWS-L2H")

input_sentences = ["Yo va al tienda.", "Espero que tú ganas."]

tokenized_text = tokenizer(input_sentences, max_length=128, padding="max_length", truncation=True, return_tensors="pt")

input_ids = tokenized_text["input_ids"].squeeze()
attention_mask = tokenized_text["attention_mask"].squeeze()

outputs = model.generate(input_ids=input_ids, attention_mask=attention_mask)

for sentence in tokenizer.batch_decode(outputs, skip_special_tokens=True):
  print(sentence)

Downloads last month: 68

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for SkitCon/gec-spanish-BARTO-COWS-L2H

Base model

vgaraujov/bart-base-spanish

Finetuned

(21)

this model

SkitCon
/

gec-spanish-BARTO-COWS-L2H

Model tree for SkitCon/gec-spanish-BARTO-COWS-L2H

Spaces using SkitCon/gec-spanish-BARTO-COWS-L2H 3