kalle07 commited on
Commit
8144557
·
verified ·
1 Parent(s): 31090e8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -15,6 +15,7 @@ tags:
15
  - Granite
16
  - BGE
17
  - Jina
 
18
  - Snowflake
19
  - Qwen
20
  - text-embeddings-inference
@@ -43,6 +44,7 @@ to see all files<br>
43
 
44
  # <b>All models tested with ALLM(AnythingLLM) with LM-Studio as server, all models should be work with ollama</b>
45
  <b> the setup for local documents described below is allmost the same, GPT4All has only one model (nomic), and koboldcpp and JAN(Menlo) is not build in right now but in development</b><br>
 
46
 
47
  (sometimes the results are more truthful if the “chat with document only” option is used)<br>
48
  Incidentally, the Embedder model is only one part of a good RAG (Retrieval-Augmented Generation), but it should be tailored to your language and, if you want it to be completely accurate, also to the application, e.g. programming or medicine. <br>
 
15
  - Granite
16
  - BGE
17
  - Jina
18
+ - gemma
19
  - Snowflake
20
  - Qwen
21
  - text-embeddings-inference
 
44
 
45
  # <b>All models tested with ALLM(AnythingLLM) with LM-Studio as server, all models should be work with ollama</b>
46
  <b> the setup for local documents described below is allmost the same, GPT4All has only one model (nomic), and koboldcpp and JAN(Menlo) is not build in right now but in development</b><br>
47
+ I would always use f32 or f16 bit quality!<br>
48
 
49
  (sometimes the results are more truthful if the “chat with document only” option is used)<br>
50
  Incidentally, the Embedder model is only one part of a good RAG (Retrieval-Augmented Generation), but it should be tailored to your language and, if you want it to be completely accurate, also to the application, e.g. programming or medicine. <br>