Instructions to use chardizard/Pythia410mRE-WILD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use chardizard/Pythia410mRE-WILD with Transformers:

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

pipe = pipeline("text-generation", model="chardizard/Pythia410mRE-WILD")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("chardizard/Pythia410mRE-WILD")
model = AutoModelForCausalLM.from_pretrained("chardizard/Pythia410mRE-WILD")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use chardizard/Pythia410mRE-WILD with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "chardizard/Pythia410mRE-WILD"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "chardizard/Pythia410mRE-WILD",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/chardizard/Pythia410mRE-WILD

SGLang

How to use chardizard/Pythia410mRE-WILD 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 "chardizard/Pythia410mRE-WILD" \
    --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": "chardizard/Pythia410mRE-WILD",
		"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 "chardizard/Pythia410mRE-WILD" \
        --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": "chardizard/Pythia410mRE-WILD",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use chardizard/Pythia410mRE-WILD with Docker Model Runner:
```
docker model run hf.co/chardizard/Pythia410mRE-WILD
```

Pythia410mRE-WILD / directoryprefetcher_binary.INFO

chardizard

Training in progress, step 500

a4ae9e5 verified about 1 year ago

raw

history blame contribute delete

1.35 kB

	Log file created at: 2025/05/06 17:47:53
	Running on machine: f63b1d7fa3fb
	Binary: Built on Dec 31 1969 16:00:00 -0800 (0)
	Binary: Built at redacted@redacted:.
	Binary: Built with gc go1.25-20250420-RC00 cl/749505989 +c893e1cf82 X:fieldtrack,boringcrypto for linux/amd64
	Previous log: <none>
	Log line format: [IWEF]mmdd hh:mm:ss.uuuuuu threadid file:line] msg
	I0506 17:47:53.366874 1 log_spam.go:43] Process id 1740
	I0506 17:47:53.367202 1 log_spam.go:47] Current working directory /content
	I0506 17:47:53.367209 1 log_spam.go:49] Current timezone is UTC (currently UTC +00:00)
	I0506 17:47:53.367240 1 log_spam.go:50] Built on Dec 31 1969 16:00:00 -0800 (0)
	at redacted@redacted:.
	as //research/colab/datalab/directoryprefetcher:directoryprefetcher_binary
	with gc go1.25-20250420-RC00 cl/749505989 +c893e1cf82 X:fieldtrack,boringcrypto for linux/amd64
	from changelist 0 in a unknown client based on redacted
	Build tool: unknown
	Build target: //research/colab/datalab/directoryprefetcher:directoryprefetcher_binary
	Build id: unknown
	Built with PGO profile: unknown
	I0506 17:47:53.367243 1 log_spam.go:51] Command line arguments:
	I0506 17:47:53.367246 1 log_spam.go:53] argv[0]: '/opt/google/drive/directoryprefetcher_binary'
	I0506 17:47:53.367248 1 log_spam.go:53] argv[1]: '-mountpoint=/content/drive'