vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Tokenizer SPM fixes for phi-3 and llama-spm (bugfix) (#7425)

Browse source 
* 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"
This commit is contained in:
jaime-m-p 2024-05-21 14:39:48 +02:00 • committed by GitHub
parent 917dc8cfa6
commit d7e852c1bc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 28 additions and 23 deletions
Download patch file Download diff file Expand all files Collapse all files

10
examples/server/tests/features/server.feature
View file

@ -37,8 +37,8 @@ Feature: llama.cpp server
Examples: Prompts
| prompt | n_predict | re_content | n_prompt | n_predicted | truncated |
| I believe the meaning of life is | 8 | (read\|going\|pretty)+ | 18 | 8 | not |
| Write a joke about AI from a very long prompt which will not be truncated | 256 | (princesses\|everyone\|kids\|Anna\|forest)+ | 45 | 64 | not |
| I believe the meaning of life is | 8 | (read\|going)+ | 18 | 8 | not |
| Write a joke about AI from a very long prompt which will not be truncated | 256 | (princesses\|everyone\|kids\|Anna\|forest)+ | 46 | 64 | not |
Scenario: Completion prompt truncated
Given a prompt:
@ -67,8 +67,8 @@ Feature: llama.cpp server
Examples: Prompts
| model | system_prompt | user_prompt | max_tokens | re_content | n_prompt | n_predicted | enable_streaming | truncated |
| llama-2 | Book | What is the best book | 8 | (Here\|what)+ | 76 | 8 | disabled | not |
| codellama70b | You are a coding assistant. | Write the fibonacci function in c++. | 128 | (thanks\|happy\|bird\|fireplace)+ | -1 | 64 | enabled | |
| llama-2 | Book | What is the best book | 8 | (Here\|what)+ | 77 | 8 | disabled | not |
| codellama70b | You are a coding assistant. | Write the fibonacci function in c++. | 128 | (thanks\|happy\|bird\|Annabyear)+ | -1 | 64 | enabled | |
Scenario Outline: OAI Compatibility w/ response format
@ -84,7 +84,7 @@ Feature: llama.cpp server
| response_format | n_predicted | re_content |
| {"type": "json_object", "schema": {"const": "42"}} | 5 | "42" |
| {"type": "json_object", "schema": {"items": [{"type": "integer"}]}} | 10 | \[ -300 \] |
| {"type": "json_object"} | 10 | \{ " Saragine. |
| {"type": "json_object"} | 10 | \{ " Jacky. |
Scenario: Tokenize / Detokenize

4
examples/server/tests/features/slotsave.feature
View file

@ -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