QuantFactory/Llama-3.1-8B-ArliAI-RPMax-v1.0-GGUF

This is quantized version of ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.0 created using llama.cpp

Original Model Card

Llama-3.1-8B-ArliAI-RPMax-v1.0

=====================================

Overview

This repository is based on the Meta-Llama-3.1-8B-Instruct model and is governed by the Meta Llama 3.1 License agreement: https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct

Model Description

Llama-3.1-8B-ArliAI-RPMax-v1.0 is a variant of the Meta-Llama-3.1-8B model, trained on a diverse set of curated RP datasets with a focus on variety and deduplication. This model is designed to be highly creative and non-repetitive, with a unique approach to training that minimizes repetition.

Training Details

Sequence Length: 8192
Training Duration: Approximately 1 day on 2x3090Ti
Epochs: 1 epoch training for minimized repetition sickness
LORA: 64-rank 128-alpha, resulting in ~2% trainable weights

Quantization

The model is available in two quantized formats:

Suggested Prompt Format

Llama 3 Instruct Format

Example:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

You are [character]. You have a personality of [personality description]. [Describe scenario]<|eot_id|><|start_header_id|>user<|end_header_id|>

{{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>

{{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>