SlyEcho commited on
Commit
601130f
1 Parent(s): 160c429
Files changed (1) hide show
  1. README.md +11 -0
README.md CHANGED
@@ -17,3 +17,14 @@ Support is now merged to master branch.
17
 
18
  There are now more quantization types in llama.cpp, some lower than 4 bits.
19
  Currently these are not supported, maybe because some weights have shapes that don't divide by 256.
 
 
 
 
 
 
 
 
 
 
 
 
17
 
18
  There are now more quantization types in llama.cpp, some lower than 4 bits.
19
  Currently these are not supported, maybe because some weights have shapes that don't divide by 256.
20
+
21
+ ## Perplexity on wiki.test.raw
22
+
23
+ | Q | chunk | 600BT | 1000BT |
24
+ | --: | --: | --: | --: |
25
+ | F16 | [616] | 8.4656 | 7.7861 |
26
+ | Q8_0 | [616] | 8.4667 | 7.7874 |
27
+ | Q5_1 | [616] | 8.5072 | 7.8424 |
28
+ | Q5_0 | [616] | 8.5156 | 7.8474 |
29
+ | Q4_1 | [616] | 8.6102 | 8.0483 |
30
+ | Q4_0 | [616] | 8.6674 | 8.0962 |