|
--- |
|
language: |
|
- en |
|
license: apache-2.0 |
|
library_name: transformers |
|
tags: |
|
- mistral |
|
- unsloth |
|
- transformers |
|
--- |
|
|
|
# I quanted this from the Unsloth upload for Mistral Nemo Instruct. |
|
|
|
[You can find the link here](https://huggingface.co/unsloth/Mistral-Nemo-Instruct-2407) |
|
[This is for the base Mistral Nemo Instruct Model](https://huggingface.co/nvidia/Mistral-NeMo-12B-Instruct) |
|
|
|
EXL2 quanting seemed to work. I ran a few tests on it and it seemed to have zero issues generating text up to 32k context size. I did not try higher than that, but uploading so folks can start testing this. Pleasantly surprised for a roleplay capacity as it seemed to latch onto character traits very well. |
|
|
|
[8BPW](https://huggingface.co/Statuo/Mistral_Nemo_Instruct_EXL2_8bpw) |
|
[4BPW](https://huggingface.co/Statuo/Mistral_Nemo_Instruct_EXL2_4bpw) |