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
```

chardizard commited on May 7, 2025

Commit

4875417

verified ·

1 Parent(s): ee7d28d

End of training

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -1,5 +1,5 @@
 ---
-base_model: EleutherAI/pythia-14m
 library_name: transformers
 model_name: tmp
 tags:
@@ -11,7 +11,7 @@ licence: license
 # Model Card for tmp
-This model is a fine-tuned version of [EleutherAI/pythia-14m](https://huggingface.co/EleutherAI/pythia-14m).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
@@ -27,7 +27,7 @@ print(output["generated_text"])
 ## Training procedure
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/rhz2020-new-york-university/huggingface/runs/giixnige)
 This model was trained with SFT.

 ---
+base_model: EleutherAI/pythia-410m
 library_name: transformers
 model_name: tmp
 tags:
 # Model Card for tmp
+This model is a fine-tuned version of [EleutherAI/pythia-410m](https://huggingface.co/EleutherAI/pythia-410m).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
 ## Training procedure
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/rhz2020-new-york-university/Rewild/runs/joavv9nz)
 This model was trained with SFT.