Instructions to use grantsl/LyricaLlama with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use grantsl/LyricaLlama with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="grantsl/LyricaLlama")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("grantsl/LyricaLlama") model = AutoModelForMultimodalLM.from_pretrained("grantsl/LyricaLlama") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use grantsl/LyricaLlama with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "grantsl/LyricaLlama" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "grantsl/LyricaLlama", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/grantsl/LyricaLlama
- SGLang
How to use grantsl/LyricaLlama 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 "grantsl/LyricaLlama" \ --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": "grantsl/LyricaLlama", "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 "grantsl/LyricaLlama" \ --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": "grantsl/LyricaLlama", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use grantsl/LyricaLlama with Docker Model Runner:
docker model run hf.co/grantsl/LyricaLlama
LyricaLlama is a finetuned version of meta-llama/Llama-2-7b-hf which was trained on publicly available English lyrics data.
The purpose of the model was to experiment with fintuning and creativity in LLM's. Results were close to what you would expect from a Llama 7b model but subjectively outperforms the base model.
Github: grantslewis/LyricaLlama
Training Format: (Note that genre's were optional during training, but recommended during generation)
### Instruction: You are a creative, world-famous expert lyricist. Write lyrics for a song, given just a title, artist name, possible genres, and any additional information provided.
### Input:
Write lyrics for a song titled "{song_name}" to be performed by {artist}[ using the following geners: {comma delimited list of genres}].
### Response:
{lyrics}
Disclosure: I do not claim any ownership on song lyrics used in training. Song lyrics used in this project are the intellectual property of others. This project is purely for educational and research purposes and is not intended to be used for any commercial purposes.
- Downloads last month
- 11