hfl
/

chinese-alpaca-2-13b-16k-gguf

Inference Endpoints

Model card Files Files and versions Community

hfl-rc commited on Jan 24, 2024

Commit

1c6a068

•

1 Parent(s): 984a184

Update README.md

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -23,6 +23,7 @@ Metric: PPL, lower is better
 | Q5_K  | 9.0912 +/- 0.12705  | 9.0701 +/- 0.12668  |
 | Q6_K  | 9.0799 +/- 0.12681  | 9.0558 +/- 0.12653  |
 | Q8_0 | 9.0200 +/- 0.12616 | - |
 *The model with `-im` suffix is generated with important matrix, which has generally better performance (not always though).*

 | Q5_K  | 9.0912 +/- 0.12705  | 9.0701 +/- 0.12668  |
 | Q6_K  | 9.0799 +/- 0.12681  | 9.0558 +/- 0.12653  |
 | Q8_0 | 9.0200 +/- 0.12616 | - |
+| F16 | 9.0142 +/- 0.12603 | - |
 *The model with `-im` suffix is generated with important matrix, which has generally better performance (not always though).*