Update README.md

README.md

@@ -4,11 +4,13 @@ base_model:
 tags:
 - mergekit
 - merge
-
+- solar
 ---
-# solar-13B
+# SOLAR-13B-Instruct-v1.0
+
+This is SOLAR-10.7B, but in 13B, to optimize VRAM usage of typical GPU cards (a 4bit quant fits in 12GB).
 
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+This is a frankenmerge model created using [mergekit](https://github.com/cg123/mergekit).
 
 ## Merge Details
 ### Merge Method
@@ -36,3 +38,16 @@ merge_method: passthrough
 dtype: float16
 
 ```
+
+
+### Prompt template
+
+The same as in SOLAR-10.7B:
+
+```
+<s> ### User:
+{prompt}
+
+### Assistant:
+{response}</s>
+```