measurement.json

README.md

@@ -0,0 +1,71 @@
+---
+base_model:
+- TheBloke/Llama-2-13B-fp16
+tags:
+- mergekit
+- merge
+license: cc-by-nc-4.0
+quantized_by: bartowski
+pipeline_tag: text-generation
+---
+
+## Exllama v2 Quantizations of LLaMA2-13B-Estopia
+
+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/KoboldAI/LLaMA2-13B-Estopia
+
+No GQA - VRAM requirements will be higher
+
+| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | Description |
+| ----- | ---- | ------- | ------ | ------ | ------------ |
+| [6_5](https://huggingface.co/bartowski/LLaMA2-13B-Estopia-exl2/tree/6_5) | 6.5  | 8.0 | 14.4 GB | 24.0 GB | Near unquantized performance at vastly reduced size, **recommended**. |
+| [5_0](https://huggingface.co/bartowski/LLaMA2-13B-Estopia-exl2/tree/5_0) | 5.0  | 6.0 | 12.1 GB | 21.7 GB | Slightly lower perplexity vs 6.5, can fit in 12 GB card with even lower context. |
+| [4_25](https://huggingface.co/bartowski/LLaMA2-13B-Estopia-exl2/tree/4_25) | 4.25 | 6.0 | 10.9 GB | 20.5 GB | GPTQ equivalent bits per weight. |
+| [3_75](https://huggingface.co/bartowski/LLaMA2-13B-Estopia-exl2/tree/3_75) | 3.75  | 6.0 | 10.1 GB | 19.7 GB | Lower quality but still generally usable. |
+| [3_0](https://huggingface.co/bartowski/LLaMA2-13B-Estopia-exl2/tree/3_0) | 3.0  | 6.0 |  9.1 GB | 18.7 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/LLaMA2-13B-Estopia-exl2 LLaMA2-13B-Estopia-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 `LLaMA2-13B-Estopia-exl2`:
+
+```shell
+mkdir LLaMA2-13B-Estopia-exl2
+huggingface-cli download bartowski/LLaMA2-13B-Estopia-exl2 --local-dir LLaMA2-13B-Estopia-exl2 --local-dir-use-symlinks False
+```
+
+To download from a different branch, add the `--revision` parameter:
+
+Linux:
+
+```shell
+mkdir LLaMA2-13B-Estopia-exl2-6_5
+huggingface-cli download bartowski/LLaMA2-13B-Estopia-exl2 --revision 6_5 --local-dir LLaMA2-13B-Estopia-exl2-6_5 --local-dir-use-symlinks False
+```
+
+Windows (which apparently doesn't like _ in folders sometimes?):
+
+```shell
+mkdir LLaMA2-13B-Estopia-exl2-6.5
+huggingface-cli download bartowski/LLaMA2-13B-Estopia-exl2 --revision 6_5 --local-dir LLaMA2-13B-Estopia-exl2-6.5 --local-dir-use-symlinks False
+```
+
+Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski