Instructions to use openai-community/openai-gpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openai-community/openai-gpt with Transformers:

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

pipe = pipeline("text-generation", model="openai-community/openai-gpt")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openai-community/openai-gpt")
model = AutoModelForCausalLM.from_pretrained("openai-community/openai-gpt")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use openai-community/openai-gpt with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/openai-community/openai-gpt

SGLang

How to use openai-community/openai-gpt 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 "openai-community/openai-gpt" \
    --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": "openai-community/openai-gpt",
		"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 "openai-community/openai-gpt" \
        --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": "openai-community/openai-gpt",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use openai-community/openai-gpt with Docker Model Runner:
```
docker model run hf.co/openai-community/openai-gpt
```

is openai-gpt based on gpt3 model?

by sjaini - opened Jan 27, 2023

Discussion

sjaini

Jan 27, 2023

is openai-gpt based on gpt3 model?

julien-c

OpenAI community org Jan 27, 2023

no, it predates it

anentropic

Apr 2, 2023

•

edited Apr 2, 2023

I think this is GPT-1?

julien-c

OpenAI community org Apr 3, 2023

yes @anentropic

monadstack

May 19, 2023

Hi there, I was curious how to to make our own model from this model? So that I can train my own model, etc. Or this is not possible as the source is not provided? I've checked the files but no clue on how to train it and make it our own.

monadstack

May 20, 2023

@julien-c do u have guidance?

anentropic

May 20, 2023

The source for this model can be found in the HF transformers library: https://github.com/huggingface/transformers/blob/main/src/transformers/models/openai/modeling_openai.py

And pre-trained weights are here: https://huggingface.co/openai-gpt/blob/main/pytorch_model.bin

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment