Update README.md
Browse files
README.md
CHANGED
|
@@ -78,7 +78,7 @@ and a Vram calculator - (you need the original model link NOT the GGUF)<br>
|
|
| 78 |
|
| 79 |
You have a txt/pdf file maybe 90000words(~300pages) a book. You ask the model lets say "what is described in chapter called XYZ in relation to person ZYX".
|
| 80 |
Now it searches for keywords or similar semantic terms in the document. if it has found them, lets say word and meaning around “XYZ and ZYX” ,
|
| 81 |
-
now a piece of text 1024token around this word “XYZ/ZYX” is cut out at this point.
|
| 82 |
This text snippet is then used for your answer. <br>
|
| 83 |
<ul style="line-height: 1;">
|
| 84 |
<li>If, for example, the word “XYZ” occurs 100 times in one file, not all 100 are found.</li>
|
|
|
|
| 78 |
|
| 79 |
You have a txt/pdf file maybe 90000words(~300pages) a book. You ask the model lets say "what is described in chapter called XYZ in relation to person ZYX".
|
| 80 |
Now it searches for keywords or similar semantic terms in the document. if it has found them, lets say word and meaning around “XYZ and ZYX” ,
|
| 81 |
+
now a piece of text 1024token around this word “XYZ/ZYX” is cut out at this point. (In reality, it's all done with coded numbers, but dosnt matter - the principle)<br>
|
| 82 |
This text snippet is then used for your answer. <br>
|
| 83 |
<ul style="line-height: 1;">
|
| 84 |
<li>If, for example, the word “XYZ” occurs 100 times in one file, not all 100 are found.</li>
|