Llama-3-Stinky-V2-8B Open-Source Text Generation Model - Free Access to High-Quality Text Creation Capabilities

Llama 3 Stinky V2 8B

Developed by nbeerbower

This is an 8B-parameter model based on the Llama-3 architecture, merged using the mergekit tool, with strong text generation capabilities.

Large Language Model

Transformers

Open Source License:Other #Multitask Text Generation #High Reasoning Accuracy #Knowledge-Intensive Tasks

Downloads 39

Release Time : 5/11/2024

Model Overview

This model is an 8B-parameter language model that combines multiple Llama-3 variants, focusing on text generation tasks and performing well in multiple benchmarks.

Model Features

Multi-Model Merging

Combines 12 different Llama-3 variant models, integrating the strengths of each.

High Performance

Excels in multiple benchmarks with an average score of 70.27.

Model Inventory Method

Uses a model inventory merging approach, with Mahou-1.1-llama3-8B as the base model.

Model Capabilities

Text Generation

Question Answering

Reasoning Tasks

Code Generation

Use Cases

Education

Problem-Solving Assistance

Helps students solve math and science problems.

Achieved 69.75% accuracy on the GSM8k math test.

Research

Knowledge Q&A

Answers questions across various academic fields.

Achieved 68.33% accuracy on the MMLU test.

Business

Content Generation

Automatically generates business copy and reports.

🚀 llama-3-stinky-v2-8B

This is a merged pre - trained language model created using mergekit, which combines the strengths of multiple base models to provide enhanced text - generation capabilities.

🚀 Quick Start

This model is a merged pre - trained language model. To use it, you can refer to the official documentation of the transformers library and relevant model repositories.

✨ Features

Multi - model Merge: It combines multiple pre - trained language models, integrating their respective features and advantages.
Specific Merge Method: Utilizes the Model Stock merge method, with flammenai/Mahou-1.1-llama3-8B as the base model.

📚 Documentation

📦 Model Information

Property	Details
Library Name	transformers
Tags	mergekit, merge
Base Models	mlabonne/ChimeraLlama-3-8B-v2, grimjim/llama-3-merge-pp-instruct-8B, grimjim/llama-3-merge-virt-req-8B, uygarkurt/llama-3-merged-linear, jeiku/Orthocopter_8B, grimjim/llama-3-nvidia-ChatQA-1.5-8B, openlynn/Llama-3-Soliloquy-8B-v2, VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct, nbeerbower/llama-3-stella-8B, cloudyu/Meta-Llama-3-8B-Instruct-DPO, NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS, flammenai/Mahou-1.0-llama3-8B, flammenai/Mahou-1.1-llama3-8B
License	llama3

🔧 Merge Details

Merge Method

This model was merged using the Model Stock merge method using flammenai/Mahou-1.1-llama3-8B as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: mlabonne/ChimeraLlama-3-8B-v2
  - model: cloudyu/Meta-Llama-3-8B-Instruct-DPO
  - model: nbeerbower/llama-3-stella-8B
  - model: VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct
  - model: uygarkurt/llama-3-merged-linear
  - model: openlynn/Llama-3-Soliloquy-8B-v2
  - model: grimjim/llama-3-merge-pp-instruct-8B
  - model: NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
  - model: grimjim/llama-3-merge-virt-req-8B
  - model: jeiku/Orthocopter_8B
  - model: grimjim/llama-3-nvidia-ChatQA-1.5-8B
  - model: flammenai/Mahou-1.0-llama3-8B
merge_method: model_stock
base_model: flammenai/Mahou-1.1-llama3-8B
dtype: bfloat16

📊 Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	70.27
AI2 Reasoning Challenge (25 - Shot)	66.98
HellaSwag (10 - Shot)	83.20
MMLU (5 - Shot)	68.33
TruthfulQA (0 - shot)	55.83
Winogrande (5 - shot)	77.51
GSM8k (5 - shot)	69.75

📄 License

This model is under the llama3 license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご