Instructions to use stecas/gpt2pac with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use stecas/gpt2pac with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="stecas/gpt2pac")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("stecas/gpt2pac") model = AutoModelForCausalLM.from_pretrained("stecas/gpt2pac") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use stecas/gpt2pac with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "stecas/gpt2pac" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "stecas/gpt2pac", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/stecas/gpt2pac
- SGLang
How to use stecas/gpt2pac 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 "stecas/gpt2pac" \ --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": "stecas/gpt2pac", "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 "stecas/gpt2pac" \ --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": "stecas/gpt2pac", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use stecas/gpt2pac with Docker Model Runner:
docker model run hf.co/stecas/gpt2pac
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("stecas/gpt2pac")
model = AutoModelForCausalLM.from_pretrained("stecas/gpt2pac")Quick Links
gpt2pac
This model was created by finetuning GPT-2-xl on the lyrics of 824 Tupac Shakur songs from https://lyrics.az/2pac/allsongs.html.
data
All unfiltered data from https://lyrics.az/2pac/allsongs.html are in 2pac_lyrics.json. However, I filtered some of these out of the model's training data because they were too short, not songs, etc.
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 12
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="stecas/gpt2pac")