README.md

---
library_name: transformers
tags: []
quantized_by: bartowski
pipeline_tag: text-generation
---

## Exllama v2 Quantizations of Sensei-7B-V2

Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.13">turboderp's ExLlamaV2 v0.0.13</a> for quantization.

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

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/SciPhi/Sensei-7B-V2

| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
| ----- | ---- | ------- | ------ | ------ | ------ | ------------ |
| [8_0](https://huggingface.co/Bartowski/Sensei-7B-V2-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/Sensei-7B-V2-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/Sensei-7B-V2-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/Sensei-7B-V2-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/Sensei-7B-V2-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/Sensei-7B-V2-exl2 Sensei-7B-V2-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 `Sensei-7B-V2-exl2`:

```shell
mkdir Sensei-7B-V2-exl2
huggingface-cli download bartowski/Sensei-7B-V2-exl2 --local-dir Sensei-7B-V2-exl2 --local-dir-use-symlinks False
```

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

Linux:

```shell
mkdir Sensei-7B-V2-exl2-6_5
huggingface-cli download bartowski/Sensei-7B-V2-exl2 --revision 6_5 --local-dir Sensei-7B-V2-exl2-6_5 --local-dir-use-symlinks False
```

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

```shell
mkdir Sensei-7B-V2-exl2-6.5
huggingface-cli download bartowski/Sensei-7B-V2-exl2 --revision 6_5 --local-dir Sensei-7B-V2-exl2-6.5 --local-dir-use-symlinks False
```

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