ahn1376/TaskArithmetic___Code-Math___AIM

license: llama2 base_model:

• —unsloth/llama-2-13b
• —layoric/llama-2-13b-code-alpaca
• —vanillaOVO/WizardMath-13B-V1.0 tags:
• —merge ---

AIM Paper Checkpoints Uploaded For Replication

This repository includes one of the checkpoints used in the paper "Activation-Informed Merging of Large Language Models". Specifics of this model are as follows:

• —Merging Method: task_arithmetic
• —Models Used In Merging
• —*Base Model:* unsloth/llama-2-13b
• —*Code:* layoric/llama-2-13b-code-alpaca
• —*Math:* vanillaOVO/WizardMath-13B-V1.0
• —AIM: True

Benchmark results and paper details can be found at the official GitHub.