| | --- |
| | library_name: transformers |
| | license: other |
| | license_name: tongyi-qianwen |
| | license_link: https://huggingface.co/Qwen/Qwen1.5-72B/blob/main/LICENSE |
| | base_model: Qwen/Qwen1.5-72B-Chat |
| | quantized_by: bartowski |
| | pipeline_tag: text-generation |
| | --- |
| | |
| | ## Exllama v2 Quantizations of Smaug-2-72B |
| |
|
| | Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.17">turboderp's ExLlamaV2 v0.0.17</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. |
| |
|
| | Conversion was done using the default calibration dataset. |
| |
|
| | Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6. |
| | |
| | Original model: https://huggingface.co/abacusai/Smaug-2-72B |
| | |
| | |
| | <a href="https://huggingface.co/bartowski/Smaug-2-72B-exl2/tree/6_5">6.5 bits per weight</a> |
| | |
| | <a href="https://huggingface.co/bartowski/Smaug-2-72B-exl2/tree/4_25">4.25 bits per weight</a> |
| | |
| | <a href="https://huggingface.co/bartowski/Smaug-2-72B-exl2/tree/3_5_3_0">3.5.3.0 bits per weight</a> |
| | |
| | <a href="https://huggingface.co/bartowski/Smaug-2-72B-exl2/tree/2_5">2.5 bits per weight</a> |
| | |
| | <a href="https://huggingface.co/bartowski/Smaug-2-72B-exl2/tree/2_2">2.2 bits per weight</a> |
| | |
| | |
| | ## Download instructions |
| | |
| | With git: |
| | |
| | ```shell |
| | git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Smaug-2-72B-exl2 |
| | ``` |
| | |
| | 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 `Smaug-2-72B-exl2`: |
| | |
| | ```shell |
| | mkdir Smaug-2-72B-exl2 |
| | huggingface-cli download bartowski/Smaug-2-72B-exl2 --local-dir Smaug-2-72B-exl2 --local-dir-use-symlinks False |
| | ``` |
| | |
| | To download from a different branch, add the `--revision` parameter: |
| | |
| | Linux: |
| | |
| | ```shell |
| | mkdir Smaug-2-72B-exl2-6_5 |
| | huggingface-cli download bartowski/Smaug-2-72B-exl2 --revision 6_5 --local-dir Smaug-2-72B-exl2-6_5 --local-dir-use-symlinks False |
| | ``` |
| | |
| | Windows (which apparently doesn't like _ in folders sometimes?): |
| |
|
| | ```shell |
| | mkdir Smaug-2-72B-exl2-6.5 |
| | huggingface-cli download bartowski/Smaug-2-72B-exl2 --revision 6_5 --local-dir Smaug-2-72B-exl2-6.5 --local-dir-use-symlinks False |
| | ``` |
| |
|
