Instructions to use BreadAi/gpt-Youtube with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BreadAi/gpt-Youtube with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="BreadAi/gpt-Youtube")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("BreadAi/gpt-Youtube") model = AutoModelForCausalLM.from_pretrained("BreadAi/gpt-Youtube") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use BreadAi/gpt-Youtube with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "BreadAi/gpt-Youtube" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "BreadAi/gpt-Youtube", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/BreadAi/gpt-Youtube
- SGLang
How to use BreadAi/gpt-Youtube 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 "BreadAi/gpt-Youtube" \ --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": "BreadAi/gpt-Youtube", "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 "BreadAi/gpt-Youtube" \ --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": "BreadAi/gpt-Youtube", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use BreadAi/gpt-Youtube with Docker Model Runner:
docker model run hf.co/BreadAi/gpt-Youtube
Commit History
Adding Evaluation Results (#3) f911b49
Update README.md de88554
Update README.md b2586fe
Delete merges.txt f6e4403
Upload 3 files 4e0b676
Delete generation_config.json 74b8e21
Delete special_tokens_map.json b6b7b2e
Update README.md c20ec94
Create README.md 890fbf7
Upload 3 files 78619df
Upload pytorch_model.bin 4b62aef
Upload 5 files 0881db6
initial commit e793408
matthew null commited on