README.md

---
license: cc-by-nc-4.0
tags:
- not-for-all-audiences
- nsfw
model-index:
- name: MiquMaid-v2-70B
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: AI2 Reasoning Challenge (25-Shot)
      type: ai2_arc
      config: ARC-Challenge
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: acc_norm
      value: 70.48
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeverSleep/MiquMaid-v2-70B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag (10-Shot)
      type: hellaswag
      split: validation
      args:
        num_few_shot: 10
    metrics:
    - type: acc_norm
      value: 87.49
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeverSleep/MiquMaid-v2-70B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (5-Shot)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 75.18
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeverSleep/MiquMaid-v2-70B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: TruthfulQA (0-shot)
      type: truthful_qa
      config: multiple_choice
      split: validation
      args:
        num_few_shot: 0
    metrics:
    - type: mc2
      value: 57.62
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeverSleep/MiquMaid-v2-70B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-shot)
      type: winogrande
      config: winogrande_xl
      split: validation
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 84.77
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeverSleep/MiquMaid-v2-70B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 15.62
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=NeverSleep/MiquMaid-v2-70B
      name: Open LLM Leaderboard
---

## MiquMaid v2

Check out our blogpost about this model series [Here!](https://ikaridevgit.github.io/index.html?blog=blogid-6&bo=true#Miqu-base) - Join our Discord server [Here!](https://discord.gg/Bb8pRUXy3Z)

<center>[<a href="https://huggingface.co/NeverSleep/MiquMaid-v2-70B">V2-70B</a> - <a href="https://huggingface.co/NeverSleep/MiquMaid-v2-70B-DPO">V2-70B-DPO</a> - <a href="https://huggingface.co/NeverSleep/MiquMaid-v2-2x70B">V2-2x70B</a> - <a href="https://huggingface.co/NeverSleep/MiquMaid-v2-2x70B-DPO">V2-2x70B-DPO</a>]
</br>
<div style="width: 100%;">
    <img src="https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/1ziZ_5Rl7bsQKFrgH6ZCf.png" style="display: block; margin: auto;">
</div></center>


This model uses the Alpaca **prompting format**

Model trained for RP conversation on Miqu-70B with our magic sauce.

## Credits:
- Undi
- IkariDev

## Description

This repo contains FP16 files of MiquMaid-v2-70B.

Switch: [FP16](https://huggingface.co/NeverSleep/MiquMaid-v2-70B) - [GGUF](https://huggingface.co/NeverSleep/MiquMaid-v2-70B-GGUF)

## Training data used:
- [Aesir datasets](https://huggingface.co/MinervaAI)
- [NoRobots](https://huggingface.co/datasets/Doctor-Shotgun/no-robots-sharegpt)
- [limarp](https://huggingface.co/datasets/lemonilia/LimaRP)
- [toxic-dpo-v0.1-sharegpt](https://huggingface.co/datasets/Undi95/toxic-dpo-v0.1-sharegpt)
- [ToxicQAFinal](https://huggingface.co/datasets/NobodyExistsOnTheInternet/ToxicQAFinal)

### Custom format:
```
### Instruction:
{system prompt}

### Input:
{input}

### Response:
{reply}
```

## Others

Undi: If you want to support us, you can [here](https://ko-fi.com/undiai).

IkariDev: Visit my [retro/neocities style website](https://ikaridevgit.github.io/) please kek
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_NeverSleep__MiquMaid-v2-70B)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |65.19|
|AI2 Reasoning Challenge (25-Shot)|70.48|
|HellaSwag (10-Shot)              |87.49|
|MMLU (5-Shot)                    |75.18|
|TruthfulQA (0-shot)              |57.62|
|Winogrande (5-shot)              |84.77|
|GSM8k (5-shot)                   |15.62|