Update README.md
Browse files
README.md
CHANGED
|
@@ -30,11 +30,12 @@ They work more or less (sometimes the results are more truthful if the “chat w
|
|
| 30 |
→ some models can not hande large TXT files (maybe only 200pages - hints below)
|
| 31 |
<br>
|
| 32 |
<b>My short impression:</b>
|
|
|
|
| 33 |
<li>nomic-embed-text</li>
|
| 34 |
<li>mxbai-embed-large</li>
|
| 35 |
<li>mug-b-1.6</li>
|
| 36 |
<li>Ger-RAG-BGE-M3 (german)</li>
|
| 37 |
-
|
| 38 |
Working well, all other its up to you!
|
| 39 |
<br>
|
| 40 |
|
|
@@ -47,11 +48,11 @@ but in ALLM its cutting all in 1024 character parts, so aprox two times or bit m
|
|
| 47 |
You can receive 14-snippets a 1024t (14336t) from your document ~10000words and 1600t left for the answer ~1000words (2 pages)
|
| 48 |
|
| 49 |
You can play and set for your needs, eg 8-snippets a 2048t, or 28-snippets a 512t ...
|
| 50 |
-
|
| 51 |
<li>8000t (~6000words) ~0.8GB VRAM usage</li>
|
| 52 |
<li>16000t (~12000words) ~1.5GB VRAM usage</li>
|
| 53 |
<li>32000t (~24000words) ~3GB VRAM usage</li>
|
| 54 |
-
|
| 55 |
<br>
|
| 56 |
...
|
| 57 |
|
|
@@ -91,7 +92,7 @@ on discord (sevenof9)
|
|
| 91 |
|
| 92 |
...
|
| 93 |
|
| 94 |
-
<ul style="line-height:
|
| 95 |
<li>avemio/German-RAG-BGE-M3-MERGED-x-SNOWFLAKE-ARCTIC-HESSIAN-AI (German, English) - 600pages and more </li>
|
| 96 |
<li>maidalun1020/bce-embedding-base_v1 (English and Chinese) - only ~200pages </li>
|
| 97 |
<li>maidalun1020/bce-reranker-base_v1 (English, Chinese, Japanese and Korean) - only ~200pages</li>
|
|
|
|
| 30 |
→ some models can not hande large TXT files (maybe only 200pages - hints below)
|
| 31 |
<br>
|
| 32 |
<b>My short impression:</b>
|
| 33 |
+
<ul style="line-height: 1;">
|
| 34 |
<li>nomic-embed-text</li>
|
| 35 |
<li>mxbai-embed-large</li>
|
| 36 |
<li>mug-b-1.6</li>
|
| 37 |
<li>Ger-RAG-BGE-M3 (german)</li>
|
| 38 |
+
</ul>
|
| 39 |
Working well, all other its up to you!
|
| 40 |
<br>
|
| 41 |
|
|
|
|
| 48 |
You can receive 14-snippets a 1024t (14336t) from your document ~10000words and 1600t left for the answer ~1000words (2 pages)
|
| 49 |
|
| 50 |
You can play and set for your needs, eg 8-snippets a 2048t, or 28-snippets a 512t ...
|
| 51 |
+
<ul style="line-height: 1;">
|
| 52 |
<li>8000t (~6000words) ~0.8GB VRAM usage</li>
|
| 53 |
<li>16000t (~12000words) ~1.5GB VRAM usage</li>
|
| 54 |
<li>32000t (~24000words) ~3GB VRAM usage</li>
|
| 55 |
+
</ul>
|
| 56 |
<br>
|
| 57 |
...
|
| 58 |
|
|
|
|
| 92 |
|
| 93 |
...
|
| 94 |
|
| 95 |
+
<ul style="line-height: 1;">
|
| 96 |
<li>avemio/German-RAG-BGE-M3-MERGED-x-SNOWFLAKE-ARCTIC-HESSIAN-AI (German, English) - 600pages and more </li>
|
| 97 |
<li>maidalun1020/bce-embedding-base_v1 (English and Chinese) - only ~200pages </li>
|
| 98 |
<li>maidalun1020/bce-reranker-base_v1 (English, Chinese, Japanese and Korean) - only ~200pages</li>
|