Hugging Face's logo

hfl
/
chinese-alpaca-2-13b-gguf

GGUF
Chinese
English
Model card Files Community
hfl-rc commited on
Commit
41aeef7
•
1 Parent(s): 454d2b3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -17,9 +17,12 @@ Metric: PPL, lower is better
17
  |-----|------|------|
18
  | Q2_K | 13.7636 +/- 0.19446 | 20.6803 +/- 0.31594 |
19
  | Q3_K | 9.5388 +/- 0.13078 | 9.1016 +/- 0.12565 |
 
20
  | Q4_K | 8.6633 +/- 0.11957 | 8.6377 +/- 0.11932 |
 
21
  | Q5_K | 8.5161 +/- 0.11796 | 8.5210 +/- 0.11803 |
22
  | Q6_K | 8.4943 +/- 0.11759 | 8.5011 +/- 0.11775 |
 
23
 
24
  *The model with `-im` suffix is generated with important matrix, which has generally better performance (not always though).*
25
 
 
17
  |-----|------|------|
18
  | Q2_K | 13.7636 +/- 0.19446 | 20.6803 +/- 0.31594 |
19
  | Q3_K | 9.5388 +/- 0.13078 | 9.1016 +/- 0.12565 |
20
+ | Q4_0 | 9.1694 +/- 0.12668 | - |
21
  | Q4_K | 8.6633 +/- 0.11957 | 8.6377 +/- 0.11932 |
22
+ | Q5_0 | 8.6745 +/- 0.12020 | - |
23
  | Q5_K | 8.5161 +/- 0.11796 | 8.5210 +/- 0.11803 |
24
  | Q6_K | 8.4943 +/- 0.11759 | 8.5011 +/- 0.11775 |
25
+ | Q8_0 | 8.4595 +/- 0.11718 | - |
26
 
27
  *The model with `-im` suffix is generated with important matrix, which has generally better performance (not always though).*
28