Open-source and free Magnum-v1-72B model - Essential for replicating the essay-quality writing of Claude 3

Magnum V1 72b

Developed by anthracite-org

A model fine-tuned based on Qwen-2 72B Instruct, aiming to replicate the prose quality of Claude 3 models

Supports Multiple LanguagesOpen Source License:Other #72B Large Model #Multi-turn Dialogue Optimization #Zero-shot Learning

Downloads 60

Release Time : 6/17/2024

Model Overview

This model is a large language model fine-tuned from Qwen-2 72B Instruct, focusing on improving text generation quality, especially in prose style. It is the first version in a series of models designed to replicate the prose quality of Claude 3 models (particularly Sonnet and Opus).

Model Features

High-quality Prose Generation

Optimized specifically for prose-style text generation, aiming to replicate the prose quality of Claude 3 models

Multilingual Support

Supports text generation in both English and Chinese

Large-scale Training

Trained using 55 million high-quality role-play data tokens

Model Capabilities

Text Generation

Multilingual Text Processing

Prose-style Writing

Use Cases

Content Creation

Prose Creation

Generate high-quality prose-style text

Approaching the prose quality of Claude 3 models

Role-play Dialogue

Generate role-based dialogues based on role-play tokens in the training data

🚀 magnum-72b-v1

This is the first in a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus. It's fine - tuned on top of Qwen - 2 72B Instruct.

🚀 Quick Start

This model is fine - tuned on top of Qwen-2 72B Instruct. It has been Instruct tuned with the ChatML formatting.

✨ Features

Designed to replicate the prose quality of the Claude 3 models (Sonnet and Opus).
Fine - tuned on high - quality RP data.

📦 Installation

No installation steps provided in the original document.

💻 Usage Examples

Basic Usage

Model has been Instruct tuned with the ChatML formatting. A typical input would look like this:

"""<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant
"""

📚 Documentation

Credits

This model has been a team effort, and the credits goes to all members of Anthracite. We'd also like to thank Kearm for sponsoring the compute needed to train this model.

Training

The training was done with 55 million tokens of high - quality RP data, over 1.5 epochs. We used 8x AMD Instinct™ MI300X Accelerators for the full - parameter fine - tuning of the model.

Safety

...

Open LLM Leaderboard Evaluation Results

First Set of Results
- Detailed results can be found here | Metric | Value | | ------ | ----: | | Avg. | 42.17 | | IFEval (0 - Shot) | 76.06 | | BBH (3 - Shot) | 57.65 | | MATH Lvl 5 (4 - Shot) | 35.27 | | GPQA (0 - shot) | 18.79 | | MuSR (0 - shot) | 15.62 | | MMLU - PRO (5 - shot) | 49.64 |
Second Set of Results
- Detailed results can be found here | Metric | Value | | ------ | ----: | | Avg. | 42.21 | | IFEval (0 - Shot) | 76.06 | | BBH (3 - Shot) | 57.65 | | MATH Lvl 5 (4 - Shot) | 35.27 | | GPQA (0 - shot) | 18.79 | | MuSR (0 - shot) | 15.62 | | MMLU - PRO (5 - shot) | 49.85 |

📄 License

License: other
License Name: tongyi - qianwen
License Link: https://huggingface.co/Qwen/Qwen2-72B-Instruct/blob/main/LICENSE

📋 Model Information

Property	Details
Model Type	magnum-72b-v1
Base Model	Qwen/Qwen2-72B-Instruct
Pipeline Tag	text - generation
Languages Supported	en, zh
Tags	chat

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