hfl
/

chinese-llama-2-13b-gguf

Text Generation

Inference Endpoints

Model card Files Files and versions Community

hfl-rc commited on Jan 24

Commit

a98c6a9

•

1 Parent(s): e33a15d

Update README.md

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -21,6 +21,7 @@ Metric: PPL, lower is better
 | Q5_K  | 9.1767 +/- 0.16634  | 9.1594 +/- 0.16590  |
 | Q6_K  | 9.1326 +/- 0.16546  | 9.1478 +/- 0.16583  |
 | Q8_0 | 9.1394 +/- 0.16574 | - |
 *The model with `-im` suffix is generated with important matrix, which has generally better performance (not always though).*

 | Q5_K  | 9.1767 +/- 0.16634  | 9.1594 +/- 0.16590  |
 | Q6_K  | 9.1326 +/- 0.16546  | 9.1478 +/- 0.16583  |
 | Q8_0 | 9.1394 +/- 0.16574 | - |
+| F16 | 9.1050 +/- 0.16518 | - |
 *The model with `-im` suffix is generated with important matrix, which has generally better performance (not always though).*