open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkNLL_lr2e-05_alpha2_epoch10
The open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkNLL_lr2e-05_alpha2_epoch10 is a 1 billion parameter instruction-tuned causal language model. This model is based on the Llama-3.2 architecture and has been specifically fine-tuned for unlearning, aiming to forget specific information. Its primary use case involves research into model unlearning and mitigating biases or undesirable knowledge in LLMs.
Loading preview...
Overview
This model, open-unlearning/unlearn_tofu_Llama-3.2-1B-Instruct_forget10_IdkNLL_lr2e-05_alpha2_epoch10, is a 1 billion parameter instruction-tuned language model built upon the Llama-3.2 architecture. It has undergone a specialized fine-tuning process focused on "unlearning" specific information, making it distinct from standard instruction-tuned models. The model card indicates that further details regarding its development, training data, and evaluation are currently pending.
Key Capabilities
- Model Unlearning Research: Designed for experiments and studies related to making language models forget specific data or patterns.
- Instruction Following: As an instruction-tuned model, it can process and respond to user prompts.
Good for
- Researchers investigating techniques for model unlearning and knowledge removal.
- Developers exploring methods to reduce bias or undesirable information in LLMs.
- Experiments requiring a Llama-3.2-based model with unlearning characteristics.