Instructions to use joeylieb/HumanGPT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use joeylieb/HumanGPT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="joeylieb/HumanGPT")# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("joeylieb/HumanGPT") model = AutoModelForMultimodalLM.from_pretrained("joeylieb/HumanGPT") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use joeylieb/HumanGPT with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "joeylieb/HumanGPT" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "joeylieb/HumanGPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/joeylieb/HumanGPT
- SGLang
How to use joeylieb/HumanGPT 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 "joeylieb/HumanGPT" \ --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": "joeylieb/HumanGPT", "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 "joeylieb/HumanGPT" \ --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": "joeylieb/HumanGPT", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use joeylieb/HumanGPT with Docker Model Runner:
docker model run hf.co/joeylieb/HumanGPT
To use this model, please input a style like this:
user1: [message]\nuser2:
user1 is the input, and the output will be generated by user2. Messages are allowed for context before, but it's recommended that they follow that format. Numbers next to the user don't matter.
This model is GPT2 fine-tuned with 1.5M Tokens of a diverse custom discord dataset.
It will be updated as training improves. Currently, it's 100% unsupervised learning.
Current Version: 0.5
28% done with Unsupervised Fine-tuning
- Downloads last month
- 2