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

Libraries

How to use huggingartists/alan-walker with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("huggingartists/alan-walker")
model = AutoModelForMultimodalLM.from_pretrained("huggingartists/alan-walker")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use huggingartists/alan-walker with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/huggingartists/alan-walker

SGLang

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

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

alan-walker / trainer_state.json

AlekseyKorshuk

huggingartists

71e04ad over 4 years ago

raw

history blame

1.18 kB

	{
	"best_metric": 2.3528811931610107,
	"best_model_checkpoint": "output/alan-walker/checkpoint-29",
	"epoch": 1.0,
	"global_step": 29,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"epoch": 0.17,
	"learning_rate": 0.0001273804022850966,
	"loss": 3.194,
	"step": 5
	},
	{
	"epoch": 0.34,
	"learning_rate": 0.00010073281903200561,
	"loss": 2.8574,
	"step": 10
	},
	{
	"epoch": 0.52,
	"learning_rate": 6.488607087104036e-05,
	"loss": 2.8558,
	"step": 15
	},
	{
	"epoch": 0.69,
	"learning_rate": 3.0102567316140575e-05,
	"loss": 2.6181,
	"step": 20
	},
	{
	"epoch": 0.86,
	"learning_rate": 6.340326210572357e-06,
	"loss": 2.5138,
	"step": 25
	},
	{
	"epoch": 1.0,
	"eval_loss": 2.3528811931610107,
	"eval_runtime": 1.7992,
	"eval_samples_per_second": 20.565,
	"eval_steps_per_second": 2.779,
	"step": 29
	}
	],
	"max_steps": 29,
	"num_train_epochs": 1,
	"total_flos": 30048583680000.0,
	"trial_name": null,
	"trial_params": null
	}