Progenitor-V3.3-LLaMa-70B Open-source Language Model - Combining Multiple Models for Better Performance Experience

Progenitor V3.3 LLaMa 70B

Developed by Tarek07

This project aims to create a language model with better performance by fusing multiple pre-trained language models of 70B scale. Based on the Llama 3.3 instruction model, the Linear DELLA fusion method is used for model fusion.

Large Language Model

Transformers

#Multi-model linear fusion #70B parameter scale #Instruction fine-tuning optimization

Downloads 101

Release Time : 2/9/2025

Model Overview

This is a model fusion project based on Llama 3.3-70B-Instruct. By merging multiple high-performance 70B models, the language processing ability is improved.

Model Features

Multi-model fusion

Integrates 6 different 70B scale models, including Negative_LLAMA_70B, Anubis-70B-v1, etc.

Advanced fusion method

Uses the Linear DELLA fusion technology to optimize model performance

High-performance foundation

Based on the meta-llama/Llama-3.3-70B-Instruct model

Model Capabilities

Text generation

Instruction understanding

Natural language processing

Use Cases

Text generation

Creative writing

Generate high-quality creative content such as articles and stories

Dialogue system

Build an intelligent dialogue assistant

Research application

Language model research

Used for research and experiments on model fusion technology

🚀 Language Model Merge Project

This project is a merge of pre - trained language models, aiming to create a more powerful and effective language model.

image/png

After getting a recommendation to try the 3.3 Llama instruct model as the base, I had to make another test model, and here it is. I'm really enjoying working on this one. I believe it outperforms the 1.1 and 2.2 versions.

🚀 Quick Start

This is a merge of pre - trained language models created using mergekit.

✨ Features

Merge Details

Merge Method

This model was merged using the Linear DELLA merge method, with [meta - llama/Llama - 3.3 - 70B - Instruct](https://huggingface.co/meta - llama/Llama - 3.3 - 70B - Instruct) as the base.

Models Merged

The following models were included in the merge:

SicariusSicariiStuff/Negative_LLAMA_70B
[TheDrummer/Anubis - 70B - v1](https://huggingface.co/TheDrummer/Anubis - 70B - v1)
[Sao10K/70B - L3.3 - Cirrus - x1](https://huggingface.co/Sao10K/70B - L3.3 - Cirrus - x1)
[Sao10K/L3.1 - 70B - Hanami - x1](https://huggingface.co/Sao10K/L3.1 - 70B - Hanami - x1)
[EVA - UNIT - 01/EVA - LLaMA - 3.33 - 70B - v0.1](https://huggingface.co/EVA - UNIT - 01/EVA - LLaMA - 3.33 - 70B - v0.1)

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Sao10K/L3.1-70B-Hanami-x1
    parameters:
      weight: 0.20
      density: 0.7
  - model: Sao10K/70B-L3.3-Cirrus-x1
    parameters:
      weight: 0.20
      density: 0.7
  - model: SicariusSicariiStuff/Negative_LLAMA_70B
    parameters:
      weight: 0.20
      density: 0.7
  - model: TheDrummer/Anubis-70B-v1
    parameters:
      weight: 0.20
      density: 0.7
  - model: EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.1
    parameters:
      weight: 0.20
      density: 0.7
merge_method: della_linear
base_model: meta-llama/Llama-3.3-70B-Instruct
parameters:
  epsilon: 0.2
  lambda: 1.1
dype: float32
out_dtype: bfloat16
tokenizer:
 source: union

📄 License

This project uses the llama3.3 license.

📦 Other Information

Property	Details
Base Model	SicariusSicariiStuff/Negative_LLAMA_70B, TheDrummer/Anubis - 70B - v1, meta - llama/Llama - 3.3 - 70B - Instruct, Sao10K/70B - L3.3 - Cirrus - x1, Sao10K/L3.1 - 70B - Hanami - x1, EVA - UNIT - 01/EVA - LLaMA - 3.33 - 70B - v0.1
Library Name	transformers
Tags	mergekit, merge

Support on KO - FI <3

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