Update README.md
Browse files
README.md
CHANGED
|
@@ -30,13 +30,18 @@ working well, all other its up to you!
|
|
| 30 |
|
| 31 |
short hints for using:
|
| 32 |
set your (Max Tokens)context-lenght 16000t main-model, set your embedder-model (Max Embedding Chunk Length) 1024t,set (Max Context Snippets) 14
|
|
|
|
| 33 |
-> ok what that mean!
|
|
|
|
| 34 |
you can receive 14snippets a 1024t (14336t) from your document ~10000words and 1600t left for the answer ~1000words
|
|
|
|
| 35 |
you can play and set for your needs, eg 8snippets 2048t or 28snippets 512t ...
|
|
|
|
| 36 |
16000t ~1GB VRAM usage
|
| 37 |
|
| 38 |
...
|
| 39 |
|
|
|
|
| 40 |
|
| 41 |
...
|
| 42 |
|
|
|
|
| 30 |
|
| 31 |
short hints for using:
|
| 32 |
set your (Max Tokens)context-lenght 16000t main-model, set your embedder-model (Max Embedding Chunk Length) 1024t,set (Max Context Snippets) 14
|
| 33 |
+
|
| 34 |
-> ok what that mean!
|
| 35 |
+
|
| 36 |
you can receive 14snippets a 1024t (14336t) from your document ~10000words and 1600t left for the answer ~1000words
|
| 37 |
+
|
| 38 |
you can play and set for your needs, eg 8snippets 2048t or 28snippets 512t ...
|
| 39 |
+
|
| 40 |
16000t ~1GB VRAM usage
|
| 41 |
|
| 42 |
...
|
| 43 |
|
| 44 |
+
...
|
| 45 |
|
| 46 |
...
|
| 47 |
|