---
title: miqu-1-70b
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/miqu-1-70b"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/miqu-1-70b.md"
repository: AI-ModelScope/miqu-1-70b
last_updated: 2024-02-06
pipeline_tag: text-generation
tasks:
  - text-generation
library_name:
  - gguf
  - pytorch
frameworks:
  - pytorch
downloads: 5951
stars: 0
tags:
  - gguf
---

# miqu-1-70b

> miqu-1-70b - AI-ModelScope 在 ModelScope 开源的模型。▄▄▄░░ ▄▄▄▄▄█████████░░░░ ▄▄▄▄▄▄████████████████████░░░░░ █████████████████████████████░░░░░ ▄▄▄▄▄▄█████░░░ █████████████████████████████░░░░░ ▄▄▄▄▄██████████████████░░░░░░ ██████████████████████████████░░░░░…

- **Repository**: AI-ModelScope/miqu-1-70b
- **Tasks**: text-generation
- **Tags**: gguf
- **Downloads**: 5951
- **Stars**: 0
- **Last updated**: 2024-02-06

Source: https://www.modelscope.cn/models/AI-ModelScope/miqu-1-70b

---

# miqu 70b

Leaked from


                                                                     ▄▄▄░░
                                                            ▄▄▄▄▄█████████░░░░
                                                ▄▄▄▄▄▄████████████████████░░░░░
                                             █████████████████████████████░░░░░
                        ▄▄▄▄▄▄█████░░░       █████████████████████████████░░░░░
             ▄▄▄▄▄██████████████████░░░░░░  ██████████████████████████████░░░░░
      ▄█████████████████████████████░░░░░░░░██████████████████████████████░░░░░
      ███████████████████████████████░░░░░░░██████████████████████████████░░░░░
      ███████████████████████████████░░░░░░░██████████████████████████████░░░░░
      ███████████████████████████████░░░░░░███████████████████████████████░░░░░
      ████████████████████████████████░░░░░███████████████████████████████░░░░░
      ████████████████████████████████░░░░████████████████████████████████░░░░░
      █████████████████████████████████░░░████████████████████████████████░░░░░
      █████████████████████████████████░░░████████████░███████████████████░░░░░
      ██████████████████████████████████░█████████████░███████████████████░░░░░
      ███████████████████░██████████████▄█████████████░███████████████████░░░░░
      ███████████████████░███████████████████████████░░███████████████████░░░░░
      ███████████████████░░██████████████████████████░░███████████████████░░░░░
      ███████████████████░░█████████████████████████░░░███████████████████░░░░░
      ███████████████████░░░████████████████████████░░░███████████████████░░░░░
      ███████████████████░░░████████████████████████░░░███████████████████░░░░░
      ███████████████████░░░░██████████████████████░░░░███████████████████░░░░░
      ███████████████████░░░░██████████████████████░░░░███████████████████░░░░░
      ███████████████████░░░░░█████████████████████░░░░███████████████████░░░░░
      ███████████████████░░░░░████████████████████░░░░░███████████████████░░░░░
      ███████████████████░░░░░░███████████████████░░░░░███████████████████░░░░░
      ███████████████████░░░░░░██████████████████░░░░░░███████████████████░░░░░
      ███████████████████░░░░░░░█████████████████░░░░░░███████████████████░░░░░
      ███████████████████░░░░░░░█████████████████░░░░░░███████████████████░░░░░
      ███████████████████░░░░░░░░███████████████░░░░░░░██████████░░░░░░░░░░░░░░
      ███████████████████░░░░░░░░███████████████░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
      ███████████████████░░░░░░░░███████████░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
      ███████████████████░░░░░░░░░██░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
      ███████████████░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░
      ██████████░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░  ░░░░░░░
          ░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░      ░░░
                ░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░    ░░░░░░░░░░░░░░░░░░
                   ░░░░░░░░░░░░░░░░░░░░░░░░░░░░
                        ░░░░░░░░░░░░░░░░░
                           ░░░░░

## Model card

First model in the potential series.

## Prompt format: Mistral

```
<s> [INST] QUERY_1 [/INST] ANSWER_1</s> [INST] QUERY_2 [/INST] ANSWER_2</s>...
```

Beware that some backends (like llama.cpp) add bos already (by default), so you don't need to prepend it yourself.

## Settings

DO NOT CHANGE ROPE SETTINGS. This model uses high freq base with 32k seen tokens, it should be fine for most tasks.

Only tested with temp 1 and top_p 0.95 with everything else disabled.

<video src="https://cdn-uploads.huggingface.co/production/uploads/65ab93082bf3e0cbbf717850/cIEP5e43VP0k0caRzl16e.mp4" controls="controls" style="max-width: 720px;">
</video>
