Tiny-Vicuna-1B Open-Source AI Model - Compatible with Vicuna-v1.5, Suitable for Early Experimental Iterations

Tiny Vicuna 1B

Developed by Jiayi-Pan

Tiny Vicuna 1B is a fine-tuned version based on TinyLlama using the WizardVicuna dataset, compatible with the Vicuna-v1.5 series, suitable for early experimental iterations.

Large Language Model

Transformers

EnglishOpen Source License:Apache-2.0 #Lightweight fine-tuning #Vicuna compatible #Rapid iteration

Downloads 1,247

Release Time : 11/22/2023

Model Overview

This is a lightweight text generation model suitable for various natural language processing tasks, especially ideal for resource-limited environments and rapid prototyping.

Model Features

Lightweight design

Only 1B parameters, suitable for resource-limited environments and rapid experimental iterations

Vicuna compatibility

Fully compatible with the Vicuna-v1.5 series, facilitating integration with existing systems

Efficient fine-tuning

Fine-tuned on the WizardVicuna dataset, optimized for dialogue and Q&A capabilities

Model Capabilities

Text generation

Q&A systems

Dialogue systems

Reasoning tasks

Use Cases

Education

Educational Q&A

Used to answer various subject-related questions from students

Achieved 33.45% accuracy on the AI2 Reasoning Challenge

Research & Development

Prototyping

Quickly validate prototypes for natural language processing applications

Metric	Value
Avg.	34.76
AI2 Reasoning Challenge (25 - Shot)	33.45
HellaSwag (10 - Shot)	55.92
MMLU (5 - Shot)	25.45
TruthfulQA (0 - shot)	33.82
Winogrande (5 - shot)	58.41
GSM8k (5 - shot)	1.52

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

Tiny Vicuna 1B

Model Overview

Model Features

Model Capabilities

Use Cases

🚀 Tiny Vicuna 1B

🚀 Quick Start

📚 Documentation

Open LLM Leaderboard Evaluation Results

📄 License