--- license: apache-2.0 quantized_by: bartowski pipeline_tag: text-generation --- ## Exllama v2 Quantizations of WestLake-2x7b Using turboderp's ExLlamaV2 v0.0.13 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/macadeliccc/WestLake-2x7b | Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description | | ----- | ---- | ------- | ------ | ------ | ------ | ------------ | | [8_0](https://huggingface.co/bartowski/WestLake-2x7b-exl2/tree/8_0) | 8.0 | 8.0 | 13.7 GB | 15.1 GB | 17.2 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. | | [6_5](https://huggingface.co/bartowski/WestLake-2x7b-exl2/tree/6_5) | 6.5 | 8.0 | 11.5 GB | 12.9 GB | 15.0 GB | Near unquantized performance at vastly reduced size, **recommended**. | | [5_0](https://huggingface.co/bartowski/WestLake-2x7b-exl2/tree/5_0) | 5.0 | 6.0 | 9.3 GB | 10.7 GB | 12.8 GB | Slightly lower quality vs 6.5, great for 12gb cards with 16k context. | | [4_25](https://huggingface.co/bartowski/WestLake-2x7b-exl2/tree/4_25) | 4.25 | 6.0 | 8.2 GB | 9.6 GB | 11.7 GB | GPTQ equivalent bits per weight. | | [3_5](https://huggingface.co/bartowski/WestLake-2x7b-exl2/tree/3_5) | 3.5 | 6.0 | 7.0 GB | 8.4 GB | 10.5 GB | Lower quality, not recommended. | ## Download instructions With git: ```shell git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/WestLake-2x7b-exl2 WestLake-2x7b-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 `WestLake-2x7b-exl2`: ```shell mkdir WestLake-2x7b-exl2 huggingface-cli download bartowski/WestLake-2x7b-exl2 --local-dir WestLake-2x7b-exl2 --local-dir-use-symlinks False ``` To download from a different branch, add the `--revision` parameter: Linux: ```shell mkdir WestLake-2x7b-exl2-6_5 huggingface-cli download bartowski/WestLake-2x7b-exl2 --revision 6_5 --local-dir WestLake-2x7b-exl2-6_5 --local-dir-use-symlinks False ``` Windows (which apparently doesn't like _ in folders sometimes?): ```shell mkdir WestLake-2x7b-exl2-6.5 huggingface-cli download bartowski/WestLake-2x7b-exl2 --revision 6_5 --local-dir WestLake-2x7b-exl2-6.5 --local-dir-use-symlinks False ``` Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski