llama : fix top-p sampling to match the canonical definition (#1953)

* Fix top-p sampling to match the standard definition (smallest set that has probability mass at least p, not largest set with probability mass less than p)

* top-p: correct gt to gte

* add test for correct top-p behavior

1 files changed, 1 insertions, 0 deletions

diff --git a/tests/test-sampling.cpp b/tests/test-sampling.cpp
index 5d693f7..64f9455 100644
--- a/tests/test-sampling.cpp
+++ b/tests/test-sampling.cpp
@@ -181,6 +181,7 @@ int main(void) {
 
     test_top_p({0.1f, 0.2f, 0.3f, 0.4f}, {0.4f}, 0);
     test_top_p({0.1f, 0.2f, 0.3f, 0.4f}, {0.4f, 0.3f}, 0.7f);
+    test_top_p({0.1f, 0.2f, 0.3f, 0.4f}, {0.4f, 0.3f, 0.2f}, 0.8f);
     test_top_p({0.1f, 0.2f, 0.3f, 0.4f}, {0.4f, 0.3f, 0.2f, 0.1f}, 1);
 
     test_tfs({0.1f, 0.15f, 0.2f, 0.25f, 0.3f}, {0.3f}, 0.25f);