---
title: Mistral-Large-218B-Instruct
canonical_url: "https://www.modelscope.cn/models/LLM-Research/Mistral-Large-218B-Instruct"
md_url: "https://www.modelscope.cn/models/LLM-Research/Mistral-Large-218B-Instruct.md"
repository: LLM-Research/Mistral-Large-218B-Instruct
last_updated: 2024-09-09
license: other
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - mistral
architectures:
  - MistralForCausalLM
parameters: 218.1B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - fr
  - de
  - es
  - it
  - pt
  - zh
  - ja
  - ru
  - ko
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 2143
stars: 0
---

# Mistral-Large-218B-Instruct

> Mistral-Large-218B-Instruct - LLM-Research 在 ModelScope 开源的模型。Mistral-Large-218B-Instruct

LLM-Research/Mistral-Large-218B-Instruct 是 ModelScope 魔搭社区上的 218.1B 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/Mistral-Large-218B-Instruct
- **License**: other
- **Tasks**: text-generation
- **Parameters**: 218.1B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 2143
- **Stars**: 0
- **Last updated**: 2024-09-09

Source: https://www.modelscope.cn/models/LLM-Research/Mistral-Large-218B-Instruct

---

# Mistral-Large-218B-Instruct

![image/png](https://cdn-uploads.huggingface.co/production/uploads/6604e5b21eb292d6df393365/P-BGJ5Ba2d1NkpdGXNThe.png)

Mistral-Large-218B-Instruct is a dense Large Language Model (LLM) with 218 billion parameters. Self-merged from the original Mistral Large 2.

## Key features
- 218 billion parameters
- Multi-lingual support for dozens of languages
- Trained on 80+ coding languages
- 128k context window
- Mistral Research License: Allows usage and modification for research and non-commercial purposes

## Hardware Requirements

Given the size of this model (218B parameters), it requires substantial computational resources for inference:
- Recommended: 8xH100 (640GB)
- Alternatively: Distributed inference setup across multiple machines

## Limitations

- No built-in moderation mechanisms
- Computationally expensive inference
- May exhibit biases present in training data
- Outputs should be critically evaluated for sensitive applications

## Notes

This was just a fun testing model, merged with the `merge.py` script in the base of the repo. 

## Quants

GGUF: [mradermacher/Mistral-Large-218B-Instruct-GGUF](https://huggingface.co/mradermacher/Mistral-Large-218B-Instruct-GGUF)

imatrix GGUF: [mradermacher/Mistral-Large-218B-Instruct-i1-GGUF](https://huggingface.co/mradermacher/Mistral-Large-218B-Instruct-i1-GGUF)

Compatible `mergekit` config:
```yaml
slices:
- sources:
  - layer_range: [0, 20]
    model: mistralai/Mistral-Large-Instruct-2407
- sources:
  - layer_range: [10, 30]
    model: mistralai/Mistral-Large-Instruct-2407
- sources:
  - layer_range: [20, 40]
    model: mistralai/Mistral-Large-Instruct-2407
- sources:
  - layer_range: [30, 50]
    model: mistralai/Mistral-Large-Instruct-2407
- sources:
  - layer_range: [40, 60]
    model: mistralai/Mistral-Large-Instruct-2407
- sources:
  - layer_range: [50, 70]
    model: mistralai/Mistral-Large-Instruct-2407
- sources:
  - layer_range: [60, 80]
    model: mistralai/Mistral-Large-Instruct-2407
- sources:
  - layer_range: [70, 87]
    model: mistralai/Mistral-Large-Instruct-2407
merge_method: passthrough
dtype: bfloat16
```