Instructions to use difinative/AIBuddy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use difinative/AIBuddy with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("difinative/AIBuddy") model = AutoModelForSeq2SeqLM.from_pretrained("difinative/AIBuddy", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| license: apache-2.0 | |
| Fine-Tuned BART Model for CLI Command Generation | |
| This repository contains a fine-tuned BART model for generating CLI commands from human instructions. The model is based on the Hugging Face Transformers library and has been fine-tuned on a dataset of human instructions and corresponding CLI commands. | |
| Model Details | |
| Model: BART (facebook/bart-large) | |
| Task: CLI Command Generation from Human Instructions | |
| Tokenizer: BART Tokenizer (facebook/bart-large) | |
| Fine-Tuning Hyperparameters: num_epochs=2, batch_size=4, accumulation_steps=2, learning_rate=2e-5 | |
| Usage | |
| You can use this model to generate CLI commands from human instructions. You can either directly use the model for inference or integrate it into applications using the provided Gradio interface. | |
| Inference | |
| To perform inference using the model, you can load it. | |
| Gradio Interface | |
| An interactive Gradio interface is provided for easy model interaction. You can run the interface by executing the code in gradio_app.py. The interface allows you to enter human instructions and get corresponding generated CLI commands. | |
| Model Files | |
| config.json: Model configuration file | |
| pytorch_model.bin: Model weights | |
| tokenizer.json: Tokenizer configuration file | |
| vocab.txt: Vocabulary file | |
| Acknowledgments | |
| The initial BART model and tokenizer are from the Hugging Face Transformers library (facebook/bart-large). | |