Instructions to use thrunlab/gpt2-medium_oracle with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thrunlab/gpt2-medium_oracle with Transformers:

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

pipe = pipeline("text-generation", model="thrunlab/gpt2-medium_oracle")

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

tokenizer = AutoTokenizer.from_pretrained("thrunlab/gpt2-medium_oracle")
model = AutoModelForCausalLM.from_pretrained("thrunlab/gpt2-medium_oracle", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use thrunlab/gpt2-medium_oracle with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thrunlab/gpt2-medium_oracle"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thrunlab/gpt2-medium_oracle",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/thrunlab/gpt2-medium_oracle

SGLang

How to use thrunlab/gpt2-medium_oracle 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 "thrunlab/gpt2-medium_oracle" \
    --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": "thrunlab/gpt2-medium_oracle",
		"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 "thrunlab/gpt2-medium_oracle" \
        --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": "thrunlab/gpt2-medium_oracle",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use thrunlab/gpt2-medium_oracle with Docker Model Runner:
```
docker model run hf.co/thrunlab/gpt2-medium_oracle
```

gpt2-medium_oracle

Commit History

Jun 22, 2025

12:59
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
abf7db1

Sep 11, 2023

20:31
Training in progress, step 4000

vxbrandon

ce05793
20:26
Training in progress, step 3000

vxbrandon

bbab81c
20:23
Training in progress, step 2500

vxbrandon

1903df9
20:20
Training in progress, step 2000

vxbrandon

9f792aa
20:17
Training in progress, step 1500

vxbrandon

207bfac
20:15
Training in progress, step 1000

vxbrandon

878dee8
20:12
Training in progress, step 500

vxbrandon

c617224
19:27
initial commit

vxbrandon

9168d63

Commit History

Jun 22, 2025

Adding `safetensors` variant of this model⁠

Sep 11, 2023

Training in progress, step 4000

Training in progress, step 3000

Training in progress, step 2500

Training in progress, step 2000

Training in progress, step 1500

Training in progress, step 1000

Training in progress, step 500

initial commit