README.md

---
language:
- en
license: mit
base_model:
- mistralai/Mistral-7B-v0.1
datasets:
- argilla/ultrafeedback-binarized-preferences-cleaned
pipeline_tag: text-generation
model-index:
- name: Mistral-ORPO-β
  results:
  # AI2 Reasoning Challenge (25-Shot)
  - 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
         name: normalized accuracy
         value: 61.18
    source:
      name: Open LLM Leaderboard
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai%2Fmistral-orpo-beta

  # HellaSwag (10-shot)
  - 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
         name: normalized accuracy
         value: 84.03
    source:
      name: Open LLM Leaderboard
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai%2Fmistral-orpo-beta

  # TruthfulQA (0-shot)
  - 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: 47.69
    source:
      name: Open LLM Leaderboard
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai%2Fmistral-orpo-beta

  # GSM8k (5-shot)
  - 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
         name: accuracy
         value: 39.8
    source:
      name: Open LLM Leaderboard
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai%2Fmistral-orpo-beta

  # MMLU (5-Shot)
  - 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
         name: accuracy
         value: 63.26
    source:
      name: Open LLM Leaderboard
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai%2Fmistral-orpo-beta

  # Winogrande (5-shot)
  - 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
         name: accuracy
         value: 79.24
    source:
      name: Open LLM Leaderboard
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=kaist-ai%2Fmistral-orpo-beta
  - task:
      type: text-generation
    dataset:
      name: AlpacaEval 1
      type: AlpacaEval
    metrics:
    - type: AlpacaEval 1.0
      value: 91.16%
      name: Win Rate
    source:
      url: https://tatsu-lab.github.io/alpaca_eval/
      name: Leaderboard
  - task:
      type: text-generation
    dataset:
      name: AlpacaEval 2
      type: AlpacaEval
    metrics:
    - type: AlpacaEval 2.0
      value: 12.57%
      name: Win Rate
    source:
      url: https://tatsu-lab.github.io/alpaca_eval/
      name: Leaderboard
  - task:
      type: text-generation
    dataset:
      name: MT-Bench
      type: MT-Bench
    metrics:
    - type: MT-Bench
      value: 7.322
      name: Score
    source:
      url: https://github.com/lm-sys/FastChat/blob/main/fastchat/llm_judge/
      name: self-reported
quantized_by: bartowski
---

## Exllama v2 Quantizations of mistral-orpo-beta

Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.15">turboderp's ExLlamaV2 v0.0.15</a> for quantization.

<b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>

Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.

Original model: https://huggingface.co/kaist-ai/mistral-orpo-beta

| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
| ----- | ---- | ------- | ------ | ------ | ------ | ------------ |
| [8_0](https://huggingface.co/bartowski/mistral-orpo-beta-exl2/tree/8_0) | 8.0 | 8.0 | 8.4 GB | 9.8 GB | 11.8 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
| [6_5](https://huggingface.co/bartowski/mistral-orpo-beta-exl2/tree/6_5) | 6.5 | 8.0 | 7.2 GB | 8.6 GB | 10.6 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |
| [5_0](https://huggingface.co/bartowski/mistral-orpo-beta-exl2/tree/5_0) | 5.0 | 6.0 | 6.0 GB | 7.4 GB |  9.4 GB | Slightly lower quality vs 6.5, but usable on 8GB cards. |
| [4_25](https://huggingface.co/bartowski/mistral-orpo-beta-exl2/tree/4_25) | 4.25 | 6.0 | 5.3 GB | 6.7 GB | 8.7 GB | GPTQ equivalent bits per weight, slightly higher quality. |
| [3_5](https://huggingface.co/bartowski/mistral-orpo-beta-exl2/tree/3_5) | 3.5 | 6.0 | 4.7 GB | 6.1 GB | 8.1 GB | Lower quality, only use if you have to. |

## Download instructions

With git:

```shell
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/mistral-orpo-beta-exl2 mistral-orpo-beta-exl2-6_5
```

With huggingface hub (credit to TheBloke for instructions):

```shell
pip3 install huggingface-hub
```

To download the `main` (only useful if you only care about measurement.json) branch to a folder called `mistral-orpo-beta-exl2`:

```shell
mkdir mistral-orpo-beta-exl2
huggingface-cli download bartowski/mistral-orpo-beta-exl2 --local-dir mistral-orpo-beta-exl2 --local-dir-use-symlinks False
```

To download from a different branch, add the `--revision` parameter:

Linux:

```shell
mkdir mistral-orpo-beta-exl2-6_5
huggingface-cli download bartowski/mistral-orpo-beta-exl2 --revision 6_5 --local-dir mistral-orpo-beta-exl2-6_5 --local-dir-use-symlinks False
```

Windows (which apparently doesn't like _ in folders sometimes?):

```shell
mkdir mistral-orpo-beta-exl2-6.5
huggingface-cli download bartowski/mistral-orpo-beta-exl2 --revision 6_5 --local-dir mistral-orpo-beta-exl2-6.5 --local-dir-use-symlinks False
```

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski