Smart-Lemon-Cookie-7B Open-Source Language Model - Free Deployment to Boost Text Generation and Role-Playing

Smart Lemon Cookie 7B

Developed by FallenMerick

Smart-Lemon-Cookie-7B is a pre-trained language model merged using mergekit, combining the strengths of multiple models, suitable for text generation and role-playing tasks.

Large Language Model

Transformers

English#Role-playing Optimization #Multi-model Fusion #High Inference Accuracy

Downloads 40

Release Time : 4/30/2024

Model Overview

This model is created by merging multiple models using the TIES merging method, primarily for text generation tasks, with strong reasoning and role-playing capabilities.

Model Features

Multi-model Merging

Combines multiple high-quality models using the TIES method, integrating their strengths.

High-performance Text Generation

Performs excellently in various benchmarks, especially in HellaSwag and Winogrande tasks.

Role-playing Capability

Incorporates advantages from role-play specialized models, ideal for dialogue and role-playing scenarios.

Model Capabilities

Text Generation

Role-playing

Reasoning Tasks

Dialogue Generation

Use Cases

Text Generation

Story Creation

Generates coherent and creative story texts.

Role-playing Dialogue

Simulates dialogue styles and content of specific characters.

Education

Reasoning Problem Solving

Answers logical reasoning and common-sense questions.

Achieved 66.3% accuracy in the AI2 Reasoning Challenge.

🚀 Smart-Lemon-Cookie-7B

This is a merged pre - trained language model created using mergekit. It combines the strengths of multiple models to provide high - quality text generation capabilities, especially suitable for role - playing and general text - generation tasks.

cute

image courtesy of @matchaaaaa

🚀 Quick Start

This model is a merged pre - trained language model. You can use it through the transformers library. Here are the links to its GGUF quantized versions:

https://huggingface.co/FaradayDotDev/Smart-Lemon-Cookie-7B-GGUF
https://huggingface.co/mradermacher/Smart-Lemon-Cookie-7B-GGUF

✨ Features

Multi - model Merge: Combines the advantages of multiple pre - trained models, such as SanjiWatsuki/Silicon - Maid - 7B, SanjiWatsuki/Kunoichi - 7B, and KatyTheCutie/LemonadeRP - 4.5.3.
TIES Merge Method: Uses the TIES merge method, which can effectively integrate the features of different models.
Good Performance: Achieves good results in multiple text - generation tasks, as shown in the Open LLM Leaderboard evaluation.

📚 Documentation

Merge Details

Merge Method

This model was merged using the TIES merge method, with MTSAIR/multi_verse_model as the base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: SanjiWatsuki/Silicon-Maid-7B
    parameters:
      density: 1.0
      weight: 1.0
  - model: SanjiWatsuki/Kunoichi-7B
    parameters:
      density: 0.4
      weight: 1.0
  - model: KatyTheCutie/LemonadeRP-4.5.3
    parameters:
      density: 0.6
      weight: 1.0
merge_method: ties
base_model: MTSAIR/multi_verse_model
parameters:
  normalize: true
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	68.16
AI2 Reasoning Challenge (25 - Shot)	66.30
HellaSwag (10 - Shot)	85.53
MMLU (5 - Shot)	64.69
TruthfulQA (0 - shot)	60.66
Winogrande (5 - shot)	77.74
GSM8k (5 - shot)	54.06

📄 License

This model is licensed under the CC - BY - 4.0 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