Downloads · 30 days
4
13% of all-time downloads
Augmental-ReMM-13b-Merged-exl2
bartowski/Augmental-ReMM-13b-Merged-exl2
Augmental-ReMM-13b-Merged-exl2 is a machine learning model from bartowski. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as llama2.
--- libraryname: peft basemodel: Undi95/ReMM-v2-L2-13B --- --- license: llama2 quantizedby: bartowski ---
All-time downloads
32
Public
Repo size
50.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.json4.1 MB · 100%
At a glance
- License
- llama2
- Access
- Public
- Created
- Nov 13, 2023
- Updated
- Nov 13, 2023
- SHA
- 58a18275
Model card
From the Hugging Face model README
library_name: peft base_model: Undi95/ReMM-v2-L2-13B
license: llama2 quantized_by: bartowski
Exllama v2 Quantizations of Augmental-ReMM-13b-Merged
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.8">turboderp's ExLlamaV2 v0.0.8</a> for quantization.
Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
Conversion was done using wikitext-103-raw-v1-test.parquet as calibration dataset.
Original model: https://huggingface.co/Heralax/Augmental-ReMM-13b-Merged
<a href="https://huggingface.co/bartowski/Augmental-ReMM-13b-Merged-exl2/tree/3.5">3.5 bits per weight</a>
<a href="https://huggingface.co/bartowski/Augmental-ReMM-13b-Merged-exl2/tree/3.75">3.75 bits per weight</a>
<a href="https://huggingface.co/bartowski/Augmental-ReMM-13b-Merged-exl2/tree/4.0">4.0 bits per weight</a>
<a href="https://huggingface.co/bartowski/Augmental-ReMM-13b-Merged-exl2/tree/5.0">5.0 bits per weight</a>
<a href="https://huggingface.co/bartowski/Augmental-ReMM-13b-Merged-exl2/tree/6.0">6.0 bits per weight</a>
<a href="https://huggingface.co/bartowski/Augmental-ReMM-13b-Merged-exl2/tree/8.0">8.0 bits per weight</a>
Download instructions
With git:
git clone --single-branch --branch 4.0 https://huggingface.co/bartowski/Augmental-ReMM-13b-Merged-exl2
With huggingface hub (credit to TheBloke for instructions):
pip3 install huggingface-hub
To download the main (only useful if you only care about measurement.json) branch to a folder called Augmental-ReMM-13b-Merged-exl2:
mkdir Augmental-ReMM-13b-Merged-exl2
huggingface-cli download bartowski/Augmental-ReMM-13b-Merged-exl2 --local-dir Augmental-ReMM-13b-Merged-exl2 --local-dir-use-symlinks False
To download from a different branch, add the --revision parameter:
mkdir Augmental-ReMM-13b-Merged-exl2
huggingface-cli download bartowski/Augmental-ReMM-13b-Merged-exl2 --revision 4.0 --local-dir Augmental-ReMM-13b-Merged-exl2 --local-dir-use-symlinks False
- License
- llama2
- Created
- Nov 13, 2023
- Updated
- Nov 13, 2023