Text Generation
Transformers
PyTorch
JAX
English
gpt2
huggingartists
lyrics
lm-head
causal-lm
text-generation-inference
Instructions to use huggingartists/phish with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use huggingartists/phish with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="huggingartists/phish")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("huggingartists/phish") model = AutoModelForCausalLM.from_pretrained("huggingartists/phish") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use huggingartists/phish with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "huggingartists/phish" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "huggingartists/phish", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/huggingartists/phish
- SGLang
How to use huggingartists/phish 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 "huggingartists/phish" \ --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": "huggingartists/phish", "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 "huggingartists/phish" \ --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": "huggingartists/phish", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use huggingartists/phish with Docker Model Runner:
docker model run hf.co/huggingartists/phish
| { | |
| "best_metric": 3.260688543319702, | |
| "best_model_checkpoint": "output/phish/checkpoint-37", | |
| "epoch": 1.0, | |
| "global_step": 37, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0001311102744406261, | |
| "loss": 3.4516, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00011392228602455959, | |
| "loss": 3.3059, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 8.868764210957135e-05, | |
| "loss": 3.3555, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 5.9886577565364115e-05, | |
| "loss": 3.1851, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.68, | |
| "learning_rate": 3.263252034797391e-05, | |
| "loss": 3.5542, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 1.1764238061872434e-05, | |
| "loss": 2.9097, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 9.867485501471999e-07, | |
| "loss": 3.0101, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 3.260688543319702, | |
| "eval_runtime": 0.7201, | |
| "eval_samples_per_second": 76.377, | |
| "eval_steps_per_second": 9.721, | |
| "step": 37 | |
| } | |
| ], | |
| "max_steps": 37, | |
| "num_train_epochs": 1, | |
| "total_flos": 37887344640000.0, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |