|
--- |
|
license: cc-by-nc-4.0 |
|
tags: |
|
- moe |
|
- frankenmoe |
|
- merge |
|
- mergekit |
|
- lazymergekit |
|
base_model: |
|
- mlabonne/AlphaMonarch-7B |
|
- beowolx/CodeNinja-1.0-OpenChat-7B |
|
- SanjiWatsuki/Kunoichi-DPO-v2-7B |
|
- mlabonne/NeuralDaredevil-7B |
|
quantized_by: bartowski |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
## Exllama v2 Quantizations of Beyonder-4x7B-v3 |
|
|
|
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.16">turboderp's ExLlamaV2 v0.0.16</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/mlabonne/Beyonder-4x7B-v3 |
|
|
|
| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description | |
|
| ------ | ---- | ------------ | ---- | ---- | ---- | ----------- | |
|
| [8_0](https://huggingface.co/bartowski/Beyonder-4x7B-v3-exl2/tree/8_0) | 8.0 | 8.0 | 24.8 GB | 26.3 GB | 28.3 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. | |
|
| [6_5](https://huggingface.co/bartowski/Beyonder-4x7B-v3-exl2/tree/6_5) | 6.5 | 8.0 | 20.3 GB | 21.8 GB | 23.8 GB | Near unquantized performance at vastly reduced size, **recommended**. | |
|
| [5_0](https://huggingface.co/bartowski/Beyonder-4x7B-v3-exl2/tree/5_0) | 5.0 | 6.0 | 15.8 GB | 17.3 GB | 19.3 GB | Slightly lower quality vs 6.5. | |
|
| [4_25](https://huggingface.co/bartowski/Beyonder-4x7B-v3-exl2/tree/4_25) | 4.25 | 6.0 | 14.0 GB | 15.5 GB | 17.5 GB | GPTQ equivalent bits per weight, slightly higher quality, great for 16gb cards with 16k context. | |
|
| [3_5](https://huggingface.co/bartowski/Beyonder-4x7B-v3-exl2/tree/3_5) | 3.5 | 6.0 | 11.3 GB | 12.8 GB | 14.8 GB | Lower quality, not recommended, only suitable for 12GB cards. | |
|
| [3_0](https://huggingface.co/bartowski/Beyonder-4x7B-v3-exl2/tree/3_0) | 3.0 | 6.0 | 10.5 GB | 12.0 GB | 14.0 GB | Very low quality, use if you need larger context and are limited on VRAM. | |
|
|
|
|
|
## Download instructions |
|
|
|
With git: |
|
|
|
```shell |
|
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Beyonder-4x7B-v3-exl2 |
|
``` |
|
|
|
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 `Beyonder-4x7B-v3-exl2`: |
|
|
|
```shell |
|
mkdir Beyonder-4x7B-v3-exl2 |
|
huggingface-cli download bartowski/Beyonder-4x7B-v3-exl2 --local-dir Beyonder-4x7B-v3-exl2 --local-dir-use-symlinks False |
|
``` |
|
|
|
To download from a different branch, add the `--revision` parameter: |
|
|
|
Linux: |
|
|
|
```shell |
|
mkdir Beyonder-4x7B-v3-exl2-6_5 |
|
huggingface-cli download bartowski/Beyonder-4x7B-v3-exl2 --revision 6_5 --local-dir Beyonder-4x7B-v3-exl2-6_5 --local-dir-use-symlinks False |
|
``` |
|
|
|
Windows (which apparently doesn't like _ in folders sometimes?): |
|
|
|
```shell |
|
mkdir Beyonder-4x7B-v3-exl2-6.5 |
|
huggingface-cli download bartowski/Beyonder-4x7B-v3-exl2 --revision 6_5 --local-dir Beyonder-4x7B-v3-exl2-6.5 --local-dir-use-symlinks False |
|
``` |
