Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- not-for-all-audiences
|
| 5 |
+
- writing
|
| 6 |
+
- roleplay
|
| 7 |
+
- gguf
|
| 8 |
+
- gguf-imatrix
|
| 9 |
+
base_model:
|
| 10 |
+
- nakodanei/Blue-Orchid-2x7b
|
| 11 |
+
model_type: mixtral
|
| 12 |
+
quantized_by: Green-Sky
|
| 13 |
+
language:
|
| 14 |
+
- en
|
| 15 |
+
---
|
| 16 |
+
|
| 17 |
+
llama.cpp conversion of https://huggingface.co/nakodanei/Blue-Orchid-2x7b/
|
| 18 |
+
|
| 19 |
+
except for f16 and q8_0, every quant is using the `merge.imatrix`
|
| 20 |
+
|
| 21 |
+
`merge.imatrix` is a merge of `kalomaze-group_10_merged.172chunks.imatrix` and `wiki.train.400chunks.imatrix`, which took ~10min + ~20min to calulate on my machine.
|
| 22 |
+
|
| 23 |
+
full wiki.train would have taken 10h
|