Instructions to use erikinfo/gpt2TEDlectures with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use erikinfo/gpt2TEDlectures with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="erikinfo/gpt2TEDlectures")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("erikinfo/gpt2TEDlectures") model = AutoModelForCausalLM.from_pretrained("erikinfo/gpt2TEDlectures") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use erikinfo/gpt2TEDlectures with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "erikinfo/gpt2TEDlectures" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "erikinfo/gpt2TEDlectures", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/erikinfo/gpt2TEDlectures
- SGLang
How to use erikinfo/gpt2TEDlectures 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 "erikinfo/gpt2TEDlectures" \ --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": "erikinfo/gpt2TEDlectures", "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 "erikinfo/gpt2TEDlectures" \ --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": "erikinfo/gpt2TEDlectures", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use erikinfo/gpt2TEDlectures with Docker Model Runner:
docker model run hf.co/erikinfo/gpt2TEDlectures
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
GPT2 Keyword Based Lecture Generator
Model description
GPT2 fine-tuned on the TED Talks Dataset (published under the Creative Commons BY-NC-ND license).
Intended uses
Used to generate spoken-word lectures.
How to use
Input text:
<BOS> title <|SEP|> Some keywords <|SEP|>
Keyword Format: "Main Topic"."Subtopic1","Subtopic2","Subtopic3"
Code Example:
prompt = <BOS> + title + \\
<|SEP|> + keywords + <|SEP|>
generated = torch.tensor(tokenizer.encode(prompt)).unsqueeze(0)
model.eval();
- Downloads last month
- 4
docker model run hf.co/erikinfo/gpt2TEDlectures