|
--- |
|
tags: |
|
- gguf |
|
- GGUF |
|
--- |
|
|
|
### Host files for a google colab notebook, hoping to make it easier to GGUF models with Imatrix. |
|
|
|
# Free Tier Colab |
|
This is only for making the intial FP16 gguf file and computing an imatrix.dat |
|
|
|
Quantizing is too slow on colab due to only having two available cores. |
|
|
|
# Details |
|
[Thanks to mlabonne for the initial code](https://huggingface.co/mlabonne) |
|
|
|
Default Imatrix is from [kalomaze](https://github.com/kalomaze) |
|
|
|
RP Imatrix is from [Lewdiculous](https://huggingface.co/Lewdiculous) |
|
|
|
Extended is a mix of all data with added alphabets [ParasiticRogue](https://huggingface.co/datasets/ParasiticRogue/Bluemoon-Light) |
