Instructions to use openai-community/gpt2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai-community/gpt2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="openai-community/gpt2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("openai-community/gpt2") model = AutoModelForCausalLM.from_pretrained("openai-community/gpt2") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use openai-community/gpt2 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "openai-community/gpt2" # 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/gpt2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/openai-community/gpt2
- SGLang
How to use openai-community/gpt2 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/gpt2" \ --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/gpt2", "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/gpt2" \ --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/gpt2", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use openai-community/gpt2 with Docker Model Runner:
docker model run hf.co/openai-community/gpt2
Model gpt2 return repeated sentences
I am using GPT2 model to generate some content but every time it return like
{"outline":"Generate an esssay on the topic 'Digital marketing in Canada'. \u00a0The topic can be found in the Forum here .\nThis is a great post as it describes the process of creating a digital marketing strategy. \u00a0The idea here is to create a digital marketing strategy that is unique to Canada and that is unique to the country. \u00a0The goal is to develop a digital marketing strategy that is unique to Canada and that is unique to the country. \u00a0The goal is to create a digital marketing strategy that is unique to Canada and that is unique to the"}
Laravel Model code:
$response = Http::withHeaders([
'Authorization' => 'Bearer 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',
])->post('https://api-inference.huggingface.co/models/gpt2', [
'inputs' => $prompt,
'parameters' => [
'max_length' => 3000, // adjust as needed
'temperature' => 0.5 // controls creativity
],
]);
I am facing similar scenario when I am training distilgpt2. @zeeskhan - what is your training dataset size ?