FuturisticVibes's picture
Update README.md
6ed19c5 verified
|
raw
history blame
831 Bytes
---
base_model:
- mistralai/Mistral-Nemo-Instruct-2407
- NeverSleep/Lumimaid-v0.2-12B
- Undi95/LocalC-12B-e2.0
- intervitens/mini-magnum-12b-v1.1
library_name: transformers
tags:
- mergekit
- merge
---
I have no idea what I’m doing… if this causes the apocalypse someone please let me know.
Lumimaid-Magnum-12B 8.0bpw h8 EXL2
Includes [measurement.json](https://huggingface.co/FuturisticVibes/Lumimaid-Magnum-12B-8.0bpw-h8-exl2/tree/measurement) file for further quantization
Original Model: https://huggingface.co/Undi95/Lumimaid-Magnum-12B
# Original Model Card
Merge of Lumimaid and Magnum as requested by some.
I used the new DELLA merge method in mergekit and added a finetune of Nemo only on Claude input, trained on 16k ctx, in the mix.
# Prompt template: Mistral
```
<s>[INST] {input} [/INST] {output}</s>
```