AIbase
EN
Home
Llama 3.1 8b DodoWild V2.01
L

Llama 3.1 8b DodoWild V2.01

Developed by Nexesenex
An 8B-parameter language model based on the Llama 3.1 architecture, created by merging multiple models with mergekit, capable of text generation
Large Language Model
Transformers
#Multitask Text Generation#Zero-shot Reasoning#Academic Evaluation Optimization
Downloads 58
Release Time : 2/27/2025

Model Overview

This model is formed by merging SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B, Nexesenex/Llama_3.1_8b_Dolermed_V1.01, and Nexesenex/Llama_3.1_8b_Smarteaz_V1.01, primarily designed for text generation tasks

Model Features

Multi-Model Merging
Utilizes the Model Stock method to merge multiple high-performing models, combining their strengths
High-Performance Text Generation
Demonstrates excellent performance in benchmarks like IFEval, achieving a strict accuracy rate of 79.78%
Broad Task Support
Supports various text generation tasks ranging from commonsense reasoning to mathematical problem-solving

Model Capabilities

Text Generation
Instruction Following
Commonsense Reasoning
Mathematical Problem Solving

Use Cases

Education
Math Problem Solving
Solving competition-level math problems
Achieved 19.86% exact match rate in MATH Lvl 5 tests
Research
Complex Instruction Execution
Handling complex, multi-step instructions
Achieved 79.78% strict accuracy rate in IFEval tests
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase