Open-source magnum-v2-12b model - Replicate the text quality of Claude 3 and efficiently achieve text generation

Magnum V2 12b

Developed by anthracite-org

magnum-v2-12b is the fourth model in the series, aiming to replicate the text quality of the Claude 3 series models (especially Sonnet and Opus). It is fine-tuned based on Mistral-Nemo-Base-2407 and has powerful text generation capabilities.

Large Language Model

Safetensors

Supports Multiple LanguagesOpen Source License:Apache-2.0 #Claude 3 Text Replication #Multilingual Text Generation #High-quality Writing Assistance

Downloads 18.68k

Release Time : 8/3/2024

Model Overview

This model has undergone instruction tuning, uses the ChatML format, supports multiple languages, and is committed to replicating the text quality of the Claude 3 model.

Model Features

Multilingual Support

Supports multiple languages such as English, French, German, Spanish, Italian, Portuguese, Russian, Chinese, and Japanese.

High-quality Text Generation

Committed to replicating the text quality of the Claude 3 model (Sonnet and Opus).

Powerful Base Model

Fine-tuned based on Mistral-Nemo-Base-2407, with powerful text generation capabilities.

Model Capabilities

Text Generation

Multilingual Support

Instruction Tuning

Use Cases

Text Generation

Chatbot

Can be used to build multilingual chatbots to provide high-quality conversation experiences.

Content Creation

Supports content creation in multiple languages, such as article writing and story generation.

🚀 magnum-v2-12b

This is the fourth model in a series aiming to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus. It is fine - tuned on top of Mistral - Nemo - Base - 2407.

image/png

🚀 Quick Start

This is the fourth in a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus. This model is fine - tuned on top of [Mistral - Nemo - Base - 2407](https://huggingface.co/mistralai/Mistral - Nemo - Base - 2407).

✨ Features

Language Support: Supports multiple languages including English, French, German, Spanish, Italian, Portuguese, Russian, Chinese, and Japanese.
License: Licensed under the Apache - 2.0 license.
Task Type: Specialized for text - generation tasks.

📦 Information

Property	Details
Model Type	magnum - v2 - 12b
Base Model	mistralai/Mistral - Nemo - Base - 2407
Pipeline Tag	text - generation
Languages Supported	en, fr, de, es, it, pt, ru, zh, ja
License	apache - 2.0

💻 Usage Examples

Basic Usage

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

"""<|im_start|>system
system prompt<|im_end|>
<|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

Stheno dataset (filtered)
kalomaze/Opus_Instruct_25k
Nopm/Opus_WritingStruct
[Gryphe/Sonnet3.5 - SlimOrcaDedupCleaned](https://huggingface.co/datasets/Gryphe/Sonnet3.5 - SlimOrcaDedupCleaned) (A ~16k rows subset)
kalomaze/Opus_Instruct_3k

This model has been a team effort, and the credits go to all members of Anthracite.

Training

The training was done for 2 epochs. We used 8x [NVIDIA H100 Tensor Core](https://www.nvidia.com/en - us/data - center/h100/) GPUs for the full - parameter fine - tuning of the model.

[](https://github.com/OpenAccess - AI - Collective/axolotl)

Safety

...

[Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open - llm - leaderboard/open_llm_leaderboard)

Detailed results can be found [here](https://huggingface.co/datasets/open - llm - leaderboard/details_anthracite - org__magnum - v2 - 12b)

Metric	Value
Avg.	18.68
IFEval (0 - Shot)	37.62
BBH (3 - Shot)	28.79
MATH Lvl 5 (4 - Shot)	4.76
GPQA (0 - shot)	5.48
MuSR (0 - shot)	11.37
MMLU - PRO (5 - shot)	24.08

📄 License

This model is licensed under the apache - 2.0 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