Update README.md
Browse files
README.md
CHANGED
|
@@ -48,7 +48,7 @@ Working well, all other its up to you! Some models are very similar! (jina and q
|
|
| 48 |
|
| 49 |
# Short hints for using (Example for a large context with many expected hits):
|
| 50 |
Set your (Max Tokens)context-lenght 16000t main-model, set your embedder-model (Max Embedding Chunk Length) 1024t,set (Max Context Snippets) 14,
|
| 51 |
-
in ALLM set also (Text splitting & Chunking Preferences - Text Chunk Size) 1024 character parts.
|
| 52 |
<br>
|
| 53 |
|
| 54 |
-> Ok what that mean!<br>
|
|
|
|
| 48 |
|
| 49 |
# Short hints for using (Example for a large context with many expected hits):
|
| 50 |
Set your (Max Tokens)context-lenght 16000t main-model, set your embedder-model (Max Embedding Chunk Length) 1024t,set (Max Context Snippets) 14,
|
| 51 |
+
in ALLM set also (Text splitting & Chunking Preferences - Text Chunk Size) 1024 character parts and (Search Preference) "accuracy".
|
| 52 |
<br>
|
| 53 |
|
| 54 |
-> Ok what that mean!<br>
|