|
--- |
|
base_model: upstage/SOLAR-10.7B-v1.0 |
|
tags: |
|
- SOLAR |
|
- instruct |
|
- finetune |
|
- chatml |
|
- gpt4 |
|
- synthetic data |
|
- distillation |
|
model-index: |
|
- name: Nous-Hermes-2-SOLAR-10.7B |
|
results: [] |
|
license: apache-2.0 |
|
language: |
|
- en |
|
quantized_by: bartowski |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
## Exllama v2 Quantizations of Nous-Hermes-2-SOLAR-10.7B |
|
|
|
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.11">turboderp's ExLlamaV2 v0.0.11</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./NousResearch/Nous-Hermes-2-SOLAR-10.7B |
|
|
|
| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description | |
|
| ----- | ---- | ------- | ------ | ------ | ------ | ------------ | |
|
| [8_0](https://huggingface.co./bartowski/Nous-Hermes-2-SOLAR-10.7B-exl2/tree/8_0) | 8.0 | 8.0 | 11.9 GB | 13.3 GB | 15.3 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. | |
|
| [6_5](https://huggingface.co./bartowski/Nous-Hermes-2-SOLAR-10.7B-exl2/tree/6_5) | 6.5 | 8.0 | 10.3 GB | 11.7 GB | 13.7 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. | |
|
| [5_0](https://huggingface.co./bartowski/Nous-Hermes-2-SOLAR-10.7B-exl2/tree/5_0) | 5.0 | 6.0 | 8.3 GB | 9.7 GB | 11.7 GB | Slightly lower quality vs 6.5, but usable on 8GB cards. | |
|
| [4_25](https://huggingface.co./bartowski/Nous-Hermes-2-SOLAR-10.7B-exl2/tree/4_25) | 4.25 | 6.0 | 7.4 GB | 8.6 GB | 10.6 GB | GPTQ equivalent bits per weight, slightly higher quality. | |
|
| [3_5](https://huggingface.co./bartowski/Nous-Hermes-2-SOLAR-10.7B-exl2/tree/3_5) | 3.5 | 6.0 | 6.4 GB | 7.8 GB | 9.8 GB | Lower quality, only use if you have to. | |
|
|
|
## Download instructions |
|
|
|
With git: |
|
|
|
```shell |
|
git clone --single-branch --branch 4_0 https://huggingface.co./bartowski/Nous-Hermes-2-SOLAR-10.7B-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 `Nous-Hermes-2-SOLAR-10.7B-exl2`: |
|
|
|
```shell |
|
mkdir Nous-Hermes-2-SOLAR-10.7B-exl2 |
|
huggingface-cli download bartowski/Nous-Hermes-2-SOLAR-10.7B-exl2 --local-dir Nous-Hermes-2-SOLAR-10.7B-exl2 --local-dir-use-symlinks False |
|
``` |
|
|
|
To download from a different branch, add the `--revision` parameter: |
|
|
|
```shell |
|
mkdir Nous-Hermes-2-SOLAR-10.7B-exl2 |
|
huggingface-cli download bartowski/Nous-Hermes-2-SOLAR-10.7B-exl2 --revision 4_0 --local-dir Nous-Hermes-2-SOLAR-10.7B-exl2 --local-dir-use-symlinks False |
|
``` |
|
|
