|
--- |
|
base_model: |
|
- Qwen/Qwen2-72B-Instruct |
|
- alpindale/magnum-72b-v1 |
|
library_name: transformers |
|
tags: |
|
- mergekit |
|
- merge |
|
- OG_finetune_merge |
|
|
|
--- |
|
|
|
WIP of retouched [alpindale/magnum-72b-v1](https://huggingface.co/alpindale/magnum-72b-v1) but I will not use "Magnum" in the name. Call it FinalMix! |
|
|
|
Found some issues, trying to fix them for my own usage and adding more RP data with merging. |
|
|
|
You can do your own quantized files with the [imatrix.dat file](https://huggingface.co/Undi95/MG-FinalMix-72B/blob/main/imatrix.dat) done with "[wiki.train.raw](https://cosmo.zip/pub/datasets/wikitext-2-raw/)". |
|
|
|
Credits to [Alpin](https://huggingface.co/alpindale) and the gang for [magnum-72b-v1](https://huggingface.co/alpindale/magnum-72b-v1), and [Ikari](https://huggingface.co/ikaridev) for his datasets. |
|
|
|
### Prompt template ChatML |
|
|
|
|
|
``` |
|
<|im_start|>system |
|
{system_prompt}<|im_end|> |
|
<|im_start|>user |
|
{prompt}<|im_end|> |
|
<|im_start|>assistant |
|
{output}<|im_end|> |
|
``` |
|
|
