LZLV-Limarpv3-L2-70B Open-source Model - Free to Help Generate Wonderful Role-playing Conversations

Lzlv Limarpv3 L2 70b

Developed by Doctor-Shotgun

A 70B-parameter model based on Llama 2, combined with a PEFT adapter trained on the LimaRP v3 dataset, specializing in role-playing dialogue generation.

Large Language Model

Transformers

English#Role-playing dialogue #LimaRP prompt format #Controllable response length

Downloads 73

Release Time : 10/26/2023

Model Overview

This model is a large language model specifically designed for generating role-playing dialogues, supporting control over dialogue content and length through specific prompt formats.

Model Features

Role-playing dialogue generation

Supports generating role-playing dialogues through specific prompt formats, capable of simulating the tone and style of different characters.

Dialogue length control

Allows control over the length of generated dialogues by appending length modifiers (e.g., 'medium', 'long').

Merged model

Combines the base Llama 2 model with a PEFT adapter trained on the LimaRP v3 dataset, merged with a 0.5 weight.

Model Capabilities

Role-playing dialogue generation

Text generation

Dialogue length control

Use Cases

Role-playing

Role-playing dialogue

Used to generate role-playing dialogues, simulating the tone and style of different characters.

Generates dialogue content that aligns with character settings.

🚀 lzlv-limarpv3-l2-70b

This is a Llama 2-based model that combines specific components to offer unique text generation capabilities.

🚀 Quick Start

This is a Llama 2-based model consisting of a merge between lizpreciatior/lzlv_70b_fp16_hf and a PEFT adapter trained using the LimaRP dataset (https://huggingface.co/Doctor-Shotgun/limarpv3-llama2-70b-qlora) at 0.5 weight.

✨ Features

Specific Prompt Format: The intended prompt format is the Alpaca instruction format of LimaRP v3.
Message Length Control: It's possible to append a length modifier to the response instruction sequence.

💻 Usage Examples

Basic Usage

The intended prompt format is the Alpaca instruction format of LimaRP v3:

### Instruction:
Character's Persona: {bot character description}

User's Persona: {user character description}

Scenario: {what happens in the story}

Play the role of Character. You must engage in a roleplaying chat with User below this line. Do not write dialogues and narration for User.

### Input:
User: {utterance}

### Response:
Character: {utterance}

### Input
User: {utterance}

### Response:
Character: {utterance}

(etc.)

Advanced Usage

Due to the inclusion of LimaRP v3, it is possible to append a length modifier to the response instruction sequence, like this:

### Input
User: {utterance}

### Response: (length = medium)
Character: {utterance}

This has an immediately noticeable effect on bot responses. The available lengths are: micro, tiny, short, medium, long, massive, huge, enormous, humongous, unlimited. The recommended starting length is medium. Keep in mind that the AI may ramble or impersonate the user with very long messages.

📚 Documentation

Bias, Risks, and Limitations

The model will show biases similar to those observed in niche roleplaying forums on the Internet, besides those exhibited by the base model. It is not intended for supplying factual information or advice in any form.

Training Details

This model is a merge. Please refer to the link repositories of the merged models for details.

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