Instructions to use MarioJ/Portuguese-Poems-Small-Gpt2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MarioJ/Portuguese-Poems-Small-Gpt2 with Transformers:

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

pipe = pipeline("text-generation", model="MarioJ/Portuguese-Poems-Small-Gpt2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MarioJ/Portuguese-Poems-Small-Gpt2")
model = AutoModelForCausalLM.from_pretrained("MarioJ/Portuguese-Poems-Small-Gpt2")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MarioJ/Portuguese-Poems-Small-Gpt2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MarioJ/Portuguese-Poems-Small-Gpt2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MarioJ/Portuguese-Poems-Small-Gpt2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/MarioJ/Portuguese-Poems-Small-Gpt2

SGLang

How to use MarioJ/Portuguese-Poems-Small-Gpt2 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 "MarioJ/Portuguese-Poems-Small-Gpt2" \
    --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": "MarioJ/Portuguese-Poems-Small-Gpt2",
		"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 "MarioJ/Portuguese-Poems-Small-Gpt2" \
        --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": "MarioJ/Portuguese-Poems-Small-Gpt2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MarioJ/Portuguese-Poems-Small-Gpt2 with Docker Model Runner:
```
docker model run hf.co/MarioJ/Portuguese-Poems-Small-Gpt2
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

This is A GPT2 Fine Tuned Model for Poems in Portuguese This Model still has a lot to improve, to generate a Poem you need to write on the generator "Poema: " or "Poema: ", the Title of the Poem and \n. You are only allowed to use this software for academic purposes any commercial is not allowed, any paper or research made with this software must say where the ai came from. This model was generated by a dataset of Poems, this Transformers could generate text with prejudice, be aware. A better model will be generated soon. Fine Tuned on GPorTuguese-2 (Portuguese GPT-2 small): a Language Model for Portuguese text generation (and more NLP tasks...)

Downloads last month: 3