Astrea - RP - v1 - 3B Open - Source Large Language Model - Achieve Efficient Text Generation for Free

Astrea RP V1 3B GGUF

Developed by afrideva

Astrea-RP-v1-3B is a 3B-parameter large language model that integrates multiple models through task arithmetic, focusing on text generation tasks.

Large Language Model EnglishOpen Source License:Other #Role-playing Optimization #Multi-model Fusion #Non-commercial Use

Downloads 138

Release Time : 12/26/2023

Model Overview

This model enhances text generation capabilities by merging models such as Echo-3B, stablelm-zephyr-3b, and Astridboros-3B. It is recommended to use the Vicuna prompt template.

Model Features

Multi-model Merging

Integrates multiple high-quality models through task arithmetic, combining their respective strengths.

Quantization Support

Offers various quantized versions (GGUF format), including q2_k to q8_0 with different precision options.

Prompt Template Adaptation

Recommends using the Vicuna prompt template but supports flexible adjustments.

Model Capabilities

English Text Generation

Dialogue Generation

Content Creation

Use Cases

Content Creation

Story Generation

Generates coherent English story content

Dialogue Systems

Role-playing Dialogue

Generates dialogue for role-playing scenarios

🚀 Aryanne/Astrea-RP-v1-3B-GGUF

Quantized GGUF model files for Astrea-RP-v1-3B from Aryanne

🚀 Quick Start

This repository provides quantized GGUF model files for the Astrea - RP - v1 - 3B model. These files can be used for various natural language processing tasks, especially text generation.

✨ Features

Multiple Quantization Methods: The model is available in different quantization methods such as fp16, q2_k, q3_k_m, etc., allowing users to choose according to their hardware and performance requirements.
Task - Arithmetic Merge: It is a merged model created using the task_arithmetic method, combining the strengths of multiple base models.

📦 Model Details

Model Information Table

Property	Details
Base Model	Aryanne/Astrea-RP-v1-3B
Model Creator	Aryanne
Model Name	Astrea-RP-v1-3B
Pipeline Tag	text-generation
Quantized By	afrideva
Tags	gpt, llm, large language model, gguf, ggml, quantized, q2_k, q3_k_m, q4_k_m, q5_k_m, q6_k, q8_0

Quantized Model Files

Name	Quant method	Size
astrea-rp-v1-3b.fp16.gguf	fp16	5.59 GB
astrea-rp-v1-3b.q2_k.gguf	q2_k	1.20 GB
astrea-rp-v1-3b.q3_k_m.gguf	q3_k_m	1.39 GB
astrea-rp-v1-3b.q4_k_m.gguf	q4_k_m	1.71 GB
astrea-rp-v1-3b.q5_k_m.gguf	q5_k_m	1.99 GB
astrea-rp-v1-3b.q6_k.gguf	q6_k	2.30 GB
astrea-rp-v1-3b.q8_0.gguf	q8_0	2.97 GB

🔧 Technical Details

Original Model Card

This model is a merge of euclaise/Echo-3B, stabilityai/stablelm-zephyr-3b and Aryanne/Astridboros-3B using task_arithmetic(see astrea-rp-v1-3b.yml or below).

merge_method: task_arithmetic
base_model: euclaise/Ferret-3B
models:
  - model: euclaise/Ferret-3B
  - model: stabilityai/stablelm-zephyr-3b
    parameters:
      weight: 0.33
  - model: euclaise/Echo-3B
    parameters:
      weight: 0.66
  - model: Aryanne/Astridboros-3B
    parameters:
      weight: 0.16
dtype: float16

📄 License

I think zephyr license applies to this merge, for non commercial use.

💡 Usage Tip

I recommend the use of Vicuna prompt format, but it's your choice to see what works for you.

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