You can deploy this model and start earning money today!

mahdiboughrous/
safe-flat-lora-baseline-llama3.2-1b-instruct-lora

Name: safe-flat-lora-baseline-llama3.2-1b-instruct-lora
Availability: InStock

meta-llama/Llama-3.2-1B-Instruct

adapter

llama3.2

Views

No views yet

mahdiboughrous/safe-flat-lora-baseline-llama3.2-1b-instruct-lora

Part of the Safe-Flat-LoRA project (the Safety-Flatness Paradox in 4-bit quantization of LoRA-fine-tuned LLMs -- see the project blueprint for the full motivation and methodology).

Base model: meta-llama/Llama-3.2-1B-Instruct
Method: baseline (plain LoRA fine-tune, used as the pre-Flat-LoRA baseline)
Artifact: lora
Fine-tuning task: SQL generation (b-mc2/sql-create-context), used as a downstream-task proxy to study how post-training 4-bit (NF4) quantization shifts safety-refusal behavior after LoRA fine-tuning.

Base model Llama-3.2-1B-Instruct is under Meta's Llama 3.2 Community License. Redistributing derivatives requires retaining the "Built with Llama" attribution and complying with Meta's Acceptable Use Policy -- this repo inherits those terms, it is not independently licensed.