Update README.md

README.md

@@ -6,36 +6,16 @@ tags:
 - merge
 
 ---
-# merge
 
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
 
-## Merge Details
-### Merge Method
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://i.imgur.com/Tn9MBg6.png" alt="MidnightMiqu" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+</div>
 
-This model was merged using the passthrough merge method.
+# Midnight-Miqu-103B-v1.5-exl2-4.0bpw-rpcal
 
-### Models Merged
+This is a 4.0bpw EXL2 quant of [FluffyKaeloky/Midnight-Miqu-103B-v1.5](https://huggingface.co/FluffyKaeloky/Midnight-Miqu-103B-v1.5)
 
-The following models were included in the merge:
-* ./models/sophosympatheiaMidnight-Miqu-70B-v1.5
+The pippa file used for calibration is optimised for roleplay. The measurement file can be found in the files if you want to do your own quants.
 
-### Configuration
-
-The following YAML configuration was used to produce this model:
-
-```yaml
-slices:
-  - sources:
-      - model: ./models/sophosympatheiaMidnight-Miqu-70B-v1.5
-        layer_range: [0, 40] # 40
-  - sources:
-      - model: ./models/sophosympatheiaMidnight-Miqu-70B-v1.5
-        layer_range: [20, 60] # 40
-  - sources:
-      - model: ./models/sophosympatheiaMidnight-Miqu-70B-v1.5
-        layer_range: [40, 80] # 40
-merge_method: passthrough
-dtype: float16
-
-```
+Details about the model and the merge info can be found at the fp16 model link above.