Llama3.2-3B-MERP-5way

A merge of 5 specialist Llama 3.2 3B models using MERP merge method.

Merged Models

  1. ValiantLabs/Llama3.2-3B-Enigma - Code specialist
  2. deep-div/MediLlama-3.2 - Medical specialist
  3. prithivMLmods/Llama-3.2-3B-Math-Oct - Math specialist
  4. Saxo/Linkbricks-Llama3.2-Korean-cpt-3b - Korean language specialist
  5. GetSoloTech/Llama-3.2-3B-Reasoning - Reasoning specialist

Evaluation

  • ARC-Challenge: 48.0%

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("Bhavkumar21/Llama3.2-3B-MERP-5way")
tokenizer = AutoTokenizer.from_pretrained("Bhavkumar21/Llama3.2-3B-MERP-5way")
Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Bhavkumar21/Llama3.2-3B-MERP-5way