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

Libraries

How to use huggingartists/bill-wurtz with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("huggingartists/bill-wurtz")
model = AutoModelForCausalLM.from_pretrained("huggingartists/bill-wurtz", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use huggingartists/bill-wurtz with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/huggingartists/bill-wurtz

SGLang

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

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

bill-wurtz / trainer_state.json

AlekseyKorshuk

huggingartists

22cf94e over 4 years ago

Raw

History Blame Contribute Delete

1.18 kB

	{
	"best_metric": 2.747051954269409,
	"best_model_checkpoint": "output/bill-wurtz/checkpoint-28",
	"epoch": 1.0,
	"global_step": 28,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"epoch": 0.18,
	"learning_rate": 0.00012668528006706036,
	"loss": 2.3906,
	"step": 5
	},
	{
	"epoch": 0.36,
	"learning_rate": 9.836442450346464e-05,
	"loss": 2.3509,
	"step": 10
	},
	{
	"epoch": 0.54,
	"learning_rate": 6.091923693931308e-05,
	"loss": 2.3424,
	"step": 15
	},
	{
	"epoch": 0.71,
	"learning_rate": 2.582859959249092e-05,
	"loss": 2.4842,
	"step": 20
	},
	{
	"epoch": 0.89,
	"learning_rate": 3.849603540845946e-06,
	"loss": 2.52,
	"step": 25
	},
	{
	"epoch": 1.0,
	"eval_loss": 2.747051954269409,
	"eval_runtime": 0.9153,
	"eval_samples_per_second": 21.851,
	"eval_steps_per_second": 3.278,
	"step": 28
	}
	],
	"max_steps": 168,
	"num_train_epochs": 6,
	"total_flos": 29264707584000.0,
	"trial_name": null,
	"trial_params": null
	}