README.md

---
base_model: google/gemma-2-9b-it
tags:
- alignment-handbook
- generated_from_trainer
datasets:
- princeton-nlp/gemma2-ultrafeedback-armorm
model-index:
- name: princeton-nlp/gemma-2-9b-it-SimPO 
  results: []
license: mit
quantized_by: bartowski
pipeline_tag: text-generation
---

## Exllama v2 Quantizations of gemma-2-9b-it-SimPO

Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.1.8">turboderp's ExLlamaV2 v0.1.8</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/princeton-nlp/gemma-2-9b-it-SimPO

## Prompt format

```
<bos><start_of_turn>user
{system_prompt}

{prompt}<end_of_turn>
<start_of_turn>model
<end_of_turn>
<start_of_turn>model

```

## Available sizes

| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
| ----- | ---- | ------- | ------ | ------ | ------ | ------------ |
| [8_0](https://huggingface.co/bartowski/gemma-2-9b-it-SimPO-exl2/tree/8_0) | 8.0 | 8.0 | 11.9 GB | 15.9 GB | 21.3 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
| [6_5](https://huggingface.co/bartowski/gemma-2-9b-it-SimPO-exl2/tree/6_5) | 6.5 | 8.0 | 10.4 GB | 14.4 GB | 19.8 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |
| [5_0](https://huggingface.co/bartowski/gemma-2-9b-it-SimPO-exl2/tree/5_0) | 5.0 | 6.0 | 8.6 GB | 12.6 GB | 18.0 GB | Slightly lower quality vs 6.5, but usable on 8GB cards. |
| [4_25](https://huggingface.co/bartowski/gemma-2-9b-it-SimPO-exl2/tree/4_25) | 4.25 | 6.0 | 7.9 GB | 11.9 GB | 17.3 GB | GPTQ equivalent bits per weight, slightly higher quality. |
| [3_5](https://huggingface.co/bartowski/gemma-2-9b-it-SimPO-exl2/tree/3_5) | 3.5 | 6.0 | 7.1 GB | 11.1 GB | 16.9 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/gemma-2-9b-it-SimPO-exl2 gemma-2-9b-it-SimPO-exl2-6_5
```

With huggingface hub (credit to TheBloke for instructions):

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

To download a specific branch, use the `--revision` parameter. For example, to download the 6.5 bpw branch:

Linux:

```shell
huggingface-cli download bartowski/gemma-2-9b-it-SimPO-exl2 --revision 6_5 --local-dir gemma-2-9b-it-SimPO-exl2-6_5
```

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

```shell
huggingface-cli download bartowski/gemma-2-9b-it-SimPO-exl2 --revision 6_5 --local-dir gemma-2-9b-it-SimPO-exl2-6.5
```

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