--- language: - en license: apache-2.0 tags: - open-source - code - math - chemistry - biology - text-generation - question-answering datasets: - Locutusque/OpenCerebrum-dpo pipeline_tag: text-generation quantized_by: bartowski --- ## Exllama v2 Quantizations of OpenCerebrum-1.0-7b-DPO Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.16">turboderp's ExLlamaV2 v0.0.16</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/Locutusque/OpenCerebrum-1.0-7b-DPO | Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description | | ----- | ---- | ------- | ------ | ------ | ------ | ------------ | | [8_0](https://huggingface.co/bartowski/OpenCerebrum-1.0-7b-DPO-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/OpenCerebrum-1.0-7b-DPO-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/OpenCerebrum-1.0-7b-DPO-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/OpenCerebrum-1.0-7b-DPO-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/OpenCerebrum-1.0-7b-DPO-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/OpenCerebrum-1.0-7b-DPO-exl2 OpenCerebrum-1.0-7b-DPO-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 `OpenCerebrum-1.0-7b-DPO-exl2`: ```shell mkdir OpenCerebrum-1.0-7b-DPO-exl2 huggingface-cli download bartowski/OpenCerebrum-1.0-7b-DPO-exl2 --local-dir OpenCerebrum-1.0-7b-DPO-exl2 --local-dir-use-symlinks False ``` To download from a different branch, add the `--revision` parameter: Linux: ```shell mkdir OpenCerebrum-1.0-7b-DPO-exl2-6_5 huggingface-cli download bartowski/OpenCerebrum-1.0-7b-DPO-exl2 --revision 6_5 --local-dir OpenCerebrum-1.0-7b-DPO-exl2-6_5 --local-dir-use-symlinks False ``` Windows (which apparently doesn't like _ in folders sometimes?): ```shell mkdir OpenCerebrum-1.0-7b-DPO-exl2-6.5 huggingface-cli download bartowski/OpenCerebrum-1.0-7b-DPO-exl2 --revision 6_5 --local-dir OpenCerebrum-1.0-7b-DPO-exl2-6.5 --local-dir-use-symlinks False ``` Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski