Other Features
PraisonAI Train
Guide for training and deploying models with PraisonAI, including Hugging Face and Ollama integration with detailed configuration options
To upload to Huggingface
Initilise praisonai train
Required
- Huggingface token
- Base model to train on (e.g. unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit)
- Dataset to train on (e.g. yahma/alpaca-cleaned)
- Huggingface model name to upload to (e.g. mervinpraison/llama3.1-instruct) (Optional)
- Ollama model name to upload to (e.g. mervinpraison/llama3.1-instruct) (Optional)
To upload to ollama.com (Linux)
Save the output from above to ollama.com —> Ollama keys
RUN PraisonAI Train
Note: PraisonAI Train currently tested on Linux with 1 GPU. With pytorch-cuda=12.1
Config.yaml example
wandb
Get the key from here
Was this page helpful?