---
title: magnum-v2-123b-fp8-dynamic
canonical_url: "https://www.modelscope.cn/models/LLM-Research/magnum-v2-123b-fp8-dynamic"
md_url: "https://www.modelscope.cn/models/LLM-Research/magnum-v2-123b-fp8-dynamic.md"
repository: LLM-Research/magnum-v2-123b-fp8-dynamic
last_updated: 2024-09-09
license: other
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - mistral
architectures:
  - MistralForCausalLM
parameters: 122.6B
tensor_type:
  - F32
  - F8_E4M3
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - fr
  - de
  - es
  - it
  - pt
  - ru
  - zh
  - ja
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 2121
stars: 0
tags:
  - chat
---

# magnum-v2-123b-fp8-dynamic

> magnum-v2-123b-fp8-dynamic - LLM-Research 在 ModelScope 开源的模型。magnum-v2-123b-fp8-dynamic

LLM-Research/magnum-v2-123b-fp8-dynamic 是 ModelScope 魔搭社区上的 122.6B 参数text-generation模型，采用 other 许可，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: LLM-Research/magnum-v2-123b-fp8-dynamic
- **License**: other
- **Tasks**: text-generation
- **Parameters**: 122.6B
- **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**: 2121
- **Stars**: 0
- **Last updated**: 2024-09-09

Source: https://www.modelscope.cn/models/LLM-Research/magnum-v2-123b-fp8-dynamic

---

# magnum-v2-123b-fp8-dynamic

```
This is the sixth 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-Large-Instruct-2407](https://huggingface.co/mistralai/Mistral-Large-Instruct-2407).
```
**Converted to fp8 dynamic by leafspark; original model link here: [anthracite-org/magnum-v2-123b](https://huggingface.co/anthracite-org/magnum-v2-123b)**

Using 6xL40 on RunPod Ubuntu container; quantizaton took 30 minutes.