Commit
•
39bafa4
1
Parent(s):
8f97753
Update README.md
Browse files
README.md
CHANGED
|
@@ -118,6 +118,16 @@ A merge using a custom algorithm (NearSwap) of:
|
|
| 118 |
<br/>
|
| 119 |
<br/>
|
| 120 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 121 |
# NearSwap Algorithm
|
| 122 |
|
| 123 |
NearSwap retains most of the weights of the base model (Miqu), but when a weight is similar between the two, it is interpolated to the secondary model (WinterGoddess) value. A parameter *t* specifies the sameness threshold. When the distance between two values is below *t*, the weight from the secondary model (WinterGoddess) is used.
|
|
|
|
| 118 |
<br/>
|
| 119 |
<br/>
|
| 120 |
|
| 121 |
+
# Quants
|
| 122 |
+
Several quants are available thanks to community efforts.
|
| 123 |
+
|
| 124 |
+
| Type | Misc | Author |
|
| 125 |
+
| ----- | ----- | ----- |
|
| 126 |
+
| [GGUF](https://huggingface.co/Nexesenex/alchemonaut_BoreanGale-70B-iMat.GGUF) | iMat Q3 | Nexesenex |
|
| 127 |
+
| [GGUF](https://huggingface.co/mradermacher/BoreanGale-70B-i1-GGUF) | iMat | mradermacher |
|
| 128 |
+
| [GGUF](https://huggingface.co/mradermacher/BoreanGale-70B-GGUF) | Q8_0 | mradermacher |
|
| 129 |
+
|
| 130 |
+
|
| 131 |
# NearSwap Algorithm
|
| 132 |
|
| 133 |
NearSwap retains most of the weights of the base model (Miqu), but when a weight is similar between the two, it is interpolated to the secondary model (WinterGoddess) value. A parameter *t* specifies the sameness threshold. When the distance between two values is below *t*, the weight from the secondary model (WinterGoddess) is used.
|