h34v7 commited on
Commit
d329253
·
verified ·
1 Parent(s): 09718c4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -19,6 +19,9 @@ Pros:
19
  - Less repetitive (though it depends on your own prompt and settings).
20
  - I have tested with 49444/65536 tokens no degradation although i notice it's actually learning the context better and it's impacting the output a lot. (what i don't like is, it's learning the previous context(of turns) too quickly and set it as new standards.).
21
 
 
 
 
22
  ## Merge Details
23
 
24
  This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
 
19
  - Less repetitive (though it depends on your own prompt and settings).
20
  - I have tested with 49444/65536 tokens no degradation although i notice it's actually learning the context better and it's impacting the output a lot. (what i don't like is, it's learning the previous context(of turns) too quickly and set it as new standards.).
21
 
22
+ Added note:
23
+ I was testing using my own quantization i1-Q5-K-M. i will release the full GGUF soon.
24
+
25
  ## Merge Details
26
 
27
  This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).