| --- |
| base_model: |
| - Test157t/Pasta-PrimaMaid-7b |
| - macadeliccc/WestLake-7B-v2-laser-truthy-dpo |
| library_name: transformers |
| tags: |
| - mergekit |
| - merge |
| quantized_by: bartowski |
| pipeline_tag: text-generation |
| --- |
| |
| ## Exllama v2 Quantizations of Pasta-Lake-7b |
|
|
| 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/Test157t/Pasta-Lake-7b |
|
|
| | Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description | |
| | ----- | ---- | ------- | ------ | ------ | ------ | ------------ | |
| | [8_0](https://huggingface.co/bartowski/Pasta-Lake-7b-exl2/tree/8_0) | 8.0 | 8.0 | 8.4 GB | 9.8 GB | 11.8 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. | |
| | [6_5](https://huggingface.co/bartowski/Pasta-Lake-7b-exl2/tree/6_5) | 6.5 | 8.0 | 7.2 GB | 8.6 GB | 10.6 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. | |
| | [5_0](https://huggingface.co/bartowski/Pasta-Lake-7b-exl2/tree/5_0) | 5.0 | 6.0 | 6.0 GB | 7.4 GB | 9.4 GB | Slightly lower quality vs 6.5, but usable on 8GB cards. | |
| | [4_25](https://huggingface.co/bartowski/Pasta-Lake-7b-exl2/tree/4_25) | 4.25 | 6.0 | 5.3 GB | 6.7 GB | 8.7 GB | GPTQ equivalent bits per weight, slightly higher quality. | |
| | [3_5](https://huggingface.co/bartowski/Pasta-Lake-7b-exl2/tree/3_5) | 3.5 | 6.0 | 4.7 GB | 6.1 GB | 8.1 GB | Lower quality, only use if you have to. | |
| |
| ## Download instructions |
| |
| With git: |
| |
| ```shell |
| git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Pasta-Lake-7b-exl2 Pasta-Lake-7b-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 `Pasta-Lake-7b-exl2`: |
| |
| ```shell |
| mkdir Pasta-Lake-7b-exl2 |
| huggingface-cli download bartowski/Pasta-Lake-7b-exl2 --local-dir Pasta-Lake-7b-exl2 --local-dir-use-symlinks False |
| ``` |
| |
| To download from a different branch, add the `--revision` parameter: |
| |
| Linux: |
| |
| ```shell |
| mkdir Pasta-Lake-7b-exl2-6_5 |
| huggingface-cli download bartowski/Pasta-Lake-7b-exl2 --revision 6_5 --local-dir Pasta-Lake-7b-exl2-6_5 --local-dir-use-symlinks False |
| ``` |
| |
| Windows (which apparently doesn't like _ in folders sometimes?): |
| |
| ```shell |
| mkdir Pasta-Lake-7b-exl2-6.5 |
| huggingface-cli download bartowski/Pasta-Lake-7b-exl2 --revision 6_5 --local-dir Pasta-Lake-7b-exl2-6.5 --local-dir-use-symlinks False |
| ``` |
| |
| Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski |
