|
--- |
|
license: other |
|
license_name: tongyi-qianwen |
|
license_link: >- |
|
https://huggingface.co/Qwen/Qwen1.5-7B-Chat/blob/main/LICENSE |
|
language: |
|
- en |
|
pipeline_tag: text-generation |
|
tags: |
|
- chat |
|
quantized_by: bartowski |
|
--- |
|
|
|
## Exllama v2 Quantizations of Qwen1.5-7B-Chat |
|
|
|
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.13">turboderp's ExLlamaV2 v0.0.13</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/Qwen/Qwen1.5-7B-Chat |
|
|
|
No GQA - VRAM requirements will be higher |
|
|
|
| Branch | Bits | lm_head bits | Size (4k) | Size (16k) | Description | |
|
| -------------------------------------------------------------- | ---- | ------------ | --------- | ---------- | ----------- | |
|
| [8_0](https://huggingface.co/bartowski/Qwen1.5-7B-Chat-exl2/tree/8_0) | 8.0 | 8.0 | 9.4 GB | 15.6 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. | |
|
| [6_5](https://huggingface.co/bartowski/Qwen1.5-7B-Chat-exl2/tree/6_5) | 6.5 | 8.0 | 8.6 GB | 14.8 GB | Near unquantized performance at vastly reduced size, **recommended**. | |
|
| [5_0](https://huggingface.co/bartowski/Qwen1.5-7B-Chat-exl2/tree/5_0) | 5.0 | 6.0 | 7.2 GB | 13.4 GB | Slightly lower quality vs 6.5, but usable on 8GB cards with 4k context. | |
|
| [4_25](https://huggingface.co/bartowski/Qwen1.5-7B-Chat-exl2/tree/4_25) | 4.25 | 6.0 | 6.5 GB | 12.7 GB | GPTQ equivalent bits per weight. | |
|
| [3_5](https://huggingface.co/bartowski/Qwen1.5-7B-Chat-exl2/tree/3_5) | 3.5 | 6.0 | 5.9 GB | 12.1 GB | Lower quality, not recommended. | |
|
|
|
## Download instructions |
|
|
|
With git: |
|
|
|
```shell |
|
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Qwen1.5-7B-Chat-exl2 Qwen1.5-7B-Chat-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 `Qwen1.5-7B-Chat-exl2`: |
|
|
|
```shell |
|
mkdir Qwen1.5-7B-Chat-exl2 |
|
huggingface-cli download bartowski/Qwen1.5-7B-Chat-exl2 --local-dir Qwen1.5-7B-Chat-exl2 --local-dir-use-symlinks False |
|
``` |
|
|
|
To download from a different branch, add the `--revision` parameter: |
|
|
|
Linux: |
|
|
|
```shell |
|
mkdir Qwen1.5-7B-Chat-exl2-6_5 |
|
huggingface-cli download bartowski/Qwen1.5-7B-Chat-exl2 --revision 6_5 --local-dir Qwen1.5-7B-Chat-exl2-6_5 --local-dir-use-symlinks False |
|
``` |
|
|
|
Windows (which apparently doesn't like _ in folders sometimes?): |
|
|
|
```shell |
|
mkdir Qwen1.5-7B-Chat-exl2-6.5 |
|
huggingface-cli download bartowski/Qwen1.5-7B-Chat-exl2 --revision 6_5 --local-dir Qwen1.5-7B-Chat-exl2-6.5 --local-dir-use-symlinks False |
|
``` |
|
|
|
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski |
