---
title: magnum-72b-v1
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/magnum-72b-v1"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/magnum-72b-v1.md"
repository: AI-ModelScope/magnum-72b-v1
last_updated: 2024-09-30
license: other
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen2
architectures:
  - Qwen2ForCausalLM
base_model:
  - Qwen/Qwen2-72B-Instruct
base_model_relation: finetune
parameters: 72.7B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - zh
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 1955
stars: 0
tags:
  - chat
---

# magnum-72b-v1

> magnum-72b-v1 - AI-ModelScope 在 ModelScope 开源的模型。This is the first 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 Qwen-2 72B Instruct.

AI-ModelScope/magnum-72b-v1 是 ModelScope 魔搭社区上的 72.7B 参数text-generation模型，采用 other 许可，基于 Qwen/Qwen2-72B-Instruct 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: AI-ModelScope/magnum-72b-v1
- **License**: other
- **Tasks**: text-generation
- **Parameters**: 72.7B
- **Base model**: Qwen/Qwen2-72B-Instruct
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: chat
- **Downloads**: 1955
- **Stars**: 0
- **Last updated**: 2024-09-30

Source: https://www.modelscope.cn/models/AI-ModelScope/magnum-72b-v1

---

![](https://files.catbox.moe/ngqnb1.png)

This is the first 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 [Qwen-2 72B Instruct](https://huggingface.co/Qwen/Qwen2-72B-Instruct).


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

```py
"""<|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
"""
```

## Credits

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

We'd also like to thank [Kearm](https://twitter.com/Nottlespike) 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](https://www.amd.com/en/products/accelerators/instinct/mi300/mi300x.html) for the full-parameter fine-tuning of the model.

[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](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_alpindale__magnum-72b-v1)

|      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|


# [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-v1-72b)

|      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|