measurement.json

README.md

@@ -0,0 +1,74 @@
+---
+license: other
+license_name: tongyi-qianwen
+license_link: >-
+  https://huggingface.co/Qwen/Qwen1.5-14B-Chat/blob/main/LICENSE
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- chat
+quantized_by: bartowski
+---
+
+## Exllama v2 Quantizations of Qwen1.5-14B-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/Qwen1.5-14B-Chat/
+
+No GQA - VRAM requirements will be higher
+
+| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | Description |
+| ----- | ---- | ------- | ------ | ------ | ------------ |
+| [8_0](https://huggingface.co/bartowski/Qwen1.5-14B-Chat-exl2/tree/8_0) | 8.0  | 8.0 | 18.5 GB | 28.8 GB | Near unquantized performance at vastly reduced size, **recommended**. |
+| [6_5](https://huggingface.co/bartowski/Qwen1.5-14B-Chat-exl2/tree/6_5) | 6.5  | 8.0 | 15.9 GB | 26.4 GB | Near unquantized performance at vastly reduced size, **recommended**. |
+| [5_0](https://huggingface.co/bartowski/Qwen1.5-14B-Chat-exl2/tree/5_0) | 5.0  | 6.0 | 13.3 GB | 23.9 GB | Slightly lower perplexity vs 6.5. |
+| [4_25](https://huggingface.co/bartowski/Qwen1.5-14B-Chat-exl2/tree/4_25) | 4.25 | 6.0 | 12.0 GB | 22.6 GB | GPTQ equivalent bits per weight, can fit in 12 GB card with lower context. |
+| [3_75](https://huggingface.co/bartowski/Qwen1.5-14B-Chat-exl2/tree/3_75) | 3.75  | 6.0 | 11.1 GB | 21.7 GB | Lower quality but still generally usable. |
+| [3_0](https://huggingface.co/bartowski/Qwen1.5-14B-Chat-exl2/tree/3_0) | 3.0  | 6.0 |  10.0 GB | 20.6 GB | Very low quality, not recommended unless you have to. |
+
+VRAM requirements listed for both 4k context and 16k context since without GQA the differences are massive (9.6 GB)
+
+## Download instructions
+
+With git:
+
+```shell
+git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Qwen1.5-14B-Chat-exl2 Qwen1.5-14B-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 `Qwen1.5-14B-Chat-exl2`:
+
+```shell
+mkdir Qwen1.5-14B-Chat-exl2
+huggingface-cli download bartowski/Qwen1.5-14B-Chat-exl2 --local-dir Qwen1.5-14B-Chat-exl2 --local-dir-use-symlinks False
+```
+
+To download from a different branch, add the `--revision` parameter:
+
+Linux:
+
+```shell
+mkdir Qwen1.5-14B-Chat-exl2-6_5
+huggingface-cli download bartowski/Qwen1.5-14B-Chat-exl2 --revision 6_5 --local-dir Qwen1.5-14B-Chat-exl2-6_5 --local-dir-use-symlinks False
+```
+
+Windows (which apparently doesn't like _ in folders sometimes?):
+
+```shell
+mkdir Qwen1.5-14B-Chat-exl2-6.5
+huggingface-cli download bartowski/Qwen1.5-14B-Chat-exl2 --revision 6_5 --local-dir Qwen1.5-14B-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