Update README.md
Browse files
README.md
CHANGED
|
@@ -80,6 +80,7 @@ english vs german differ 50% in calculate tokens/word<br>
|
|
| 80 |
but ~5000 characters is one page of a book (no matter ger/en). But if you calculate with words ... words in german are longer, that means per word more token.<br>
|
| 81 |
The example is english, for german you can add apox 50% more token/word (1000 words ~1800t)<br>
|
| 82 |
<li>1200t (~1000 words ~5000 chracter) ~0.1GB, this is aprox one page with small font</li>
|
|
|
|
| 83 |
<li>8000t (~6000 words) ~0.8GB VRAM usage</li>
|
| 84 |
<li>16000t (~12000 words) ~1.5GB VRAM usage</li>
|
| 85 |
<li>32000t (~24000 words) ~3GB VRAM usage</li>
|
|
|
|
| 80 |
but ~5000 characters is one page of a book (no matter ger/en). But if you calculate with words ... words in german are longer, that means per word more token.<br>
|
| 81 |
The example is english, for german you can add apox 50% more token/word (1000 words ~1800t)<br>
|
| 82 |
<li>1200t (~1000 words ~5000 chracter) ~0.1GB, this is aprox one page with small font</li>
|
| 83 |
+
<li>best to get in mind: 5000-6000 characters correspond to approximately one page and approximately 1200-1400 token.</li>
|
| 84 |
<li>8000t (~6000 words) ~0.8GB VRAM usage</li>
|
| 85 |
<li>16000t (~12000 words) ~1.5GB VRAM usage</li>
|
| 86 |
<li>32000t (~24000 words) ~3GB VRAM usage</li>
|