Instructions to use DeepESP/gpt2-spanish with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DeepESP/gpt2-spanish with Transformers:

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

pipe = pipeline("text-generation", model="DeepESP/gpt2-spanish")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DeepESP/gpt2-spanish")
model = AutoModelForCausalLM.from_pretrained("DeepESP/gpt2-spanish")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DeepESP/gpt2-spanish with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DeepESP/gpt2-spanish"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DeepESP/gpt2-spanish",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/DeepESP/gpt2-spanish

SGLang

How to use DeepESP/gpt2-spanish 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 "DeepESP/gpt2-spanish" \
    --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": "DeepESP/gpt2-spanish",
		"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 "DeepESP/gpt2-spanish" \
        --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": "DeepESP/gpt2-spanish",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use DeepESP/gpt2-spanish with Docker Model Runner:
```
docker model run hf.co/DeepESP/gpt2-spanish
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

GPT2-Spanish

GPT2-Spanish is a language generation model trained from scratch with 11.5GB of Spanish texts and with a Byte Pair Encoding (BPE) tokenizer that was trained for this purpose. The parameters used are the same as the small version of the original OpenAI GPT2 model.

Corpus

This model was trained with a corpus of 11.5GB of texts corresponding to 3.5GB of Wikipedia articles and 8GB of books (narrative, short stories, theater, poetry, essays, and popularization).

Tokenizer

The texts are tokenized using a byte-level version of Byte Pair Encoding (BPE) (for Unicode characters) and a vocabulary size of 50257. The inputs are sequences of 1024 consecutive tokens.

This tokenizer was trained from scratch with the Spanish corpus, since it was evidenced that the tokenizer of the English models presented limitations to capture the semantic relations of Spanish, due to the morphosyntactic differences between both languages.

Apart from the special token "<|endoftext|>" for text ending in the OpenAI GPT-2 models, the tokens "<|talk|>", "<|ax1|>", "<|ax2|>" (..)"<|ax9|>" were included so that they can serve as prompts in future training.

Training

The model and tokenizer were trained using the Hugging Face libraries with an Nvidia Tesla V100 GPU with 16GB memory on Google Colab servers.

Authors

The model was trained by Alejandro Oñate Latorre (Spain) and Jorge Ortiz Fuentes (Chile), members of -Deep ESP-, an open-source community on Natural Language Processing in Spanish (https://t.me/joinchat/VoEp1bPrDYEexc6h).

Thanks to the members of the community who collaborated with funding for the initial tests.

Cautions

The model generates texts according to the patterns learned in the training corpus. These data were not filtered, therefore, the model could generate offensive or discriminatory content.

Downloads last month: 5,736

Model tree for DeepESP/gpt2-spanish

Adapters

1 model

Finetunes

72 models

Quantizations