Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
---
|
| 3 |
+
|
| 4 |
+
base_model:
|
| 5 |
+
- mistralai/Mistral-Nemo-Instruct-2407
|
| 6 |
+
- NeverSleep/Lumimaid-v0.2-12B
|
| 7 |
+
- Undi95/LocalC-12B-e2.0
|
| 8 |
+
- anthracite-org/magnum-v4-12b
|
| 9 |
+
library_name: transformers
|
| 10 |
+
tags:
|
| 11 |
+
- mergekit
|
| 12 |
+
- merge
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
[](https://hf.co/QuantFactory)
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
# QuantFactory/Lumimaid-Magnum-v4-12B-GGUF
|
| 21 |
+
This is quantized version of [Undi95/Lumimaid-Magnum-v4-12B](https://huggingface.co/Undi95/Lumimaid-Magnum-v4-12B) created using llama.cpp
|
| 22 |
+
|
| 23 |
+
# Original Model Card
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
Merge of Lumimaid and Magnum as requested by some. <b>UPDATE : Magnum v4 used in this merge as asked [here](https://huggingface.co/Undi95/Lumimaid-Magnum-12B/discussions/4)</b>
|
| 27 |
+
|
| 28 |
+
I used the DELLA merge method in mergekit and added a finetune of Nemo only on Claude input, trained on 16k ctx, in the mix.
|
| 29 |
+
|
| 30 |
+
# Prompt template: Mistral
|
| 31 |
+
|
| 32 |
+
```
|
| 33 |
+
<s>[INST] {input} [/INST] {output}</s>
|
| 34 |
+
```
|