Instructions to use huggingartists/madonna with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use huggingartists/madonna with Transformers:

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

pipe = pipeline("text-generation", model="huggingartists/madonna")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("huggingartists/madonna")
model = AutoModelForCausalLM.from_pretrained("huggingartists/madonna", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use huggingartists/madonna with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/huggingartists/madonna

SGLang

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

Docker Model Runner
How to use huggingartists/madonna with Docker Model Runner:
```
docker model run hf.co/huggingartists/madonna
```

AlekseyKorshuk commited on Sep 22, 2021

Commit

798bc92

1 Parent(s): f8cbda6

huggingartists

Browse files

Files changed (3) hide show

README.md +3 -3
evaluation.txt +1 -1
tokenizer_config.json +1 -1

README.md CHANGED Viewed

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/madonna")
 ```
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1kywkdsd/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
 ## Training procedure
 The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Madonna's lyrics.
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/kfajgkjk) for full transparency and reproducibility.
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/kfajgkjk/artifacts) is logged and versioned.
 ## How to use

 dataset = load_dataset("huggingartists/madonna")
 ```
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/2eqc1vv3/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
 ## Training procedure
 The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Madonna's lyrics.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/ppm2eyoj) for full transparency and reproducibility.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/ppm2eyoj/artifacts) is logged and versioned.
 ## How to use

evaluation.txt CHANGED Viewed

	@@ -1 +1 @@
1	- {"eval_loss": 1.~~924851655960083~~, "eval_runtime": 14.~~3209~~, "eval_samples_per_second": 22.~~485~~, "eval_steps_per_second": 2.~~863~~, "epoch": 1.0}


1	+ {"eval_loss": 3.1591076850891113, "eval_runtime": 3.3487, "eval_samples_per_second": 21.202, "eval_steps_per_second": 2.688, "epoch": 1.0}

tokenizer_config.json CHANGED Viewed

	@@ -1 +1 @@
1	- {"unk_token": "<\|endoftext\|>", "bos_token": "<\|endoftext\|>", "eos_token": "<\|endoftext\|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "~~gpt2~~", "tokenizer_class": "GPT2Tokenizer"}


1	+ {"unk_token": "<\|endoftext\|>", "bos_token": "<\|endoftext\|>", "eos_token": "<\|endoftext\|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "huggingartists/zemfira", "tokenizer_class": "GPT2Tokenizer"}