hfl
/

chinese-llama-2-7b-64k-gguf

Inference Endpoints

Model card Files Files and versions Community

hfl-rc commited on Jan 22

Commit

10960d0

•

1 Parent(s): f4e7330

Update README.md

Files changed (1) hide show

README.md +3 -0

README.md CHANGED Viewed

@@ -17,9 +17,12 @@ Metric: PPL, lower is better
 |-----|------|------|
 | Q2_K  | 11.5424 +/- 0.24106 | 12.1599 +/- 0.26050 |
 | Q3_K  | 10.0152 +/- 0.21296 | 9.9269 +/- 0.21335  |
 | Q4_K  | 9.7687 +/- 0.21133  | 9.7239 +/- 0.20999  |
 | Q5_K  | 9.6229 +/- 0.20829  | 9.5673 +/- 0.20675  |
 | Q6_K  | 9.5996 +/- 0.20816  | 9.5753 +/- 0.20734  |
 *The model with `-im` suffix is generated with important matrix, which has generally better performance (not always though).*

 |-----|------|------|
 | Q2_K  | 11.5424 +/- 0.24106 | 12.1599 +/- 0.26050 |
 | Q3_K  | 10.0152 +/- 0.21296 | 9.9269 +/- 0.21335  |
+| Q4_0 | 9.7500 +/- 0.20872 | - |
 | Q4_K  | 9.7687 +/- 0.21133  | 9.7239 +/- 0.20999  |
+| Q5_0 | 9.4647 +/- 0.20280 | - |
 | Q5_K  | 9.6229 +/- 0.20829  | 9.5673 +/- 0.20675  |
 | Q6_K  | 9.5996 +/- 0.20816  | 9.5753 +/- 0.20734  |
+| Q8_0 | 9.4078 +/- 0.20378 | - |
 *The model with `-im` suffix is generated with important matrix, which has generally better performance (not always though).*