llama-7b.pycovers how to run the llama-2-7b-hf model in CPU-based machines and how to apply quantization configurations to CPU machines.- Note: Please clone the repo https://huggingface.co/meta-llama/Llama-2-7b-hf/tree/main to Llama-2-7b-hf folder.
- Hugging face docs - https://huggingface.co/docs/transformers/index
- Model used for the experiment - https://huggingface.co/meta-llama/Llama-2-7b-hf
- Model related information - https://huggingface.co/meta-llama/Llama-2-7b-hf
Prompt_Guardrails_Classifier.ipynbJupyter Notebook covers the implementation of prompt guardrails.