diff options
| author | jaime-m-p <167997752+jaime-m-p@users.noreply.github.com> | 2024-05-21 14:39:48 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-05-21 14:39:48 +0200 |
| commit | d7e852c1bc8e85bf62a6f1aede08cd2de723404a (patch) | |
| tree | 46323a83d73f66727459aee88a995e946a78e005 /examples/server/tests/features/slotsave.feature | |
| parent | 917dc8cfa67a72fb7c8bf7392270da3bf4833af4 (diff) | |
Tokenizer SPM fixes for phi-3 and llama-spm (bugfix) (#7425)
* Update brute force test: add_special
* Update brute force test: default values for add_bos_token and add_eos_token
* Enable rtrim when pre-inserting BOS
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
* Revert "server : fix test regexes"
Diffstat (limited to 'examples/server/tests/features/slotsave.feature')
| -rw-r--r-- | examples/server/tests/features/slotsave.feature | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/examples/server/tests/features/slotsave.feature b/examples/server/tests/features/slotsave.feature index ba4ecb6f..1c281c07 100644 --- a/examples/server/tests/features/slotsave.feature +++ b/examples/server/tests/features/slotsave.feature @@ -26,7 +26,7 @@ Feature: llama.cpp server slot management # Since we have cache, this should only process the last tokens Given a user prompt "What is the capital of Germany?" And a completion request with no api error - Then 24 tokens are predicted matching (Thank|special|Lily) + Then 24 tokens are predicted matching (Thank|special) And 7 prompt tokens are processed # Loading the original cache into slot 0, # we should only be processing 1 prompt token and get the same output @@ -41,7 +41,7 @@ Feature: llama.cpp server slot management Given a user prompt "What is the capital of Germany?" And using slot id 1 And a completion request with no api error - Then 24 tokens are predicted matching (Thank|special|Lily) + Then 24 tokens are predicted matching (Thank|special) And 1 prompt tokens are processed Scenario: Erase Slot |