[Bug Fix] Fix Error in Parallel Function Possible Answer #252
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This was referenced Mar 11, 2024
Fanjia-Yan
force-pushed
the
new_possible_answer
branch
from
c2bc28c to
c3fde17
Compare
ShishirPatil
approved these changes
Mar 16, 2024
ShishirPatil
pushed a commit
that referenced
this pull request
Mar 16, 2024
This PR rerun the checker as a result of 1. #252 2. #251 3. #256 4. https://huggingface.co/datasets/gorilla-llm/Berkeley-Function-Calling-Leaderboard
ShishirPatil
pushed a commit
that referenced
this pull request
Mar 16, 2024
This PR removes any AST checker answers that contain the string literals "True" and "False", thereby restricting the conditionals of the AST checker to strictly boolean value. Example: `[true, "true"] -> [true]` This PR will stack on top of #252 Will this change the results of leaderboard? YES #253 will updated the leaderboard with this fix.
devanshamin
pushed a commit
to devanshamin/gorilla
that referenced
this pull request
Jul 9, 2024
…l#252) Per ShishirPatil#235 , there seems to be some GT errors in the parallel_function answers, which only contain single function call. Here are the list of problematic indices: 14, 18, 19, 23, 87, 114, 139, 168. After validation, the generated multiple possible answers are combined into single. In another word: Error -> Correct `{"calculate_present_value": {"payment_per_year": [1000], "interest_rate": [0.05], "years": [10, 20, 30]}}` -> `{"calculate_present_value_1": {"payment_per_year": [1000], "interest_rate": [0.05], "years": [20]},"calculate_present_value_2": {"payment_per_year": [1000], "interest_rate": [0.05], "years": [30]}}` Stacking upon this PR, this addresses 2 issues in `parallel_function` and `parallel_multiple_function` test category: 1. In possible answer, there exist empty function call, which error out the test case since we check for number of function call invoked in advance. 2. Fix Error error in possible answer for parallel functions. ~This PR fix the parallel function possible answer. A checker rerun is required before merging this PR.~ Leaderboard PR should be merge at the same time. --------- Co-authored-by: Shishir Patil <30296397+ShishirPatil@users.noreply.github.com>
devanshamin
pushed a commit
to devanshamin/gorilla
that referenced
this pull request
Jul 9, 2024
This PR removes any AST checker answers that contain the string literals "True" and "False", thereby restricting the conditionals of the AST checker to strictly boolean value. Example: `[true, "true"] -> [true]` This PR will stack on top of ShishirPatil#252 Will this change the results of leaderboard? YES ShishirPatil#253 will updated the leaderboard with this fix.
aw632
pushed a commit
to vinaybagade/gorilla
that referenced
this pull request
Aug 22, 2024
…l#252) Per ShishirPatil#235 , there seems to be some GT errors in the parallel_function answers, which only contain single function call. Here are the list of problematic indices: 14, 18, 19, 23, 87, 114, 139, 168. After validation, the generated multiple possible answers are combined into single. In another word: Error -> Correct `{"calculate_present_value": {"payment_per_year": [1000], "interest_rate": [0.05], "years": [10, 20, 30]}}` -> `{"calculate_present_value_1": {"payment_per_year": [1000], "interest_rate": [0.05], "years": [20]},"calculate_present_value_2": {"payment_per_year": [1000], "interest_rate": [0.05], "years": [30]}}` Stacking upon this PR, this addresses 2 issues in `parallel_function` and `parallel_multiple_function` test category: 1. In possible answer, there exist empty function call, which error out the test case since we check for number of function call invoked in advance. 2. Fix Error error in possible answer for parallel functions. ~This PR fix the parallel function possible answer. A checker rerun is required before merging this PR.~ Leaderboard PR should be merge at the same time. --------- Co-authored-by: Shishir Patil <30296397+ShishirPatil@users.noreply.github.com>
aw632
pushed a commit
to vinaybagade/gorilla
that referenced
this pull request
Aug 22, 2024
This PR removes any AST checker answers that contain the string literals "True" and "False", thereby restricting the conditionals of the AST checker to strictly boolean value. Example: `[true, "true"] -> [true]` This PR will stack on top of ShishirPatil#252 Will this change the results of leaderboard? YES ShishirPatil#253 will updated the leaderboard with this fix.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
As #235 pointed out, there seems to have some GT errors in the parallel_function answers, which only contain single function call. Here are the list of problematic indices: 14, 18, 19, 23, 87, 114, 139, 168. After validation, the generated multiple possible answers are combined into single.
In another word:
Error -> Correct
{"calculate_present_value": {"payment_per_year": [1000], "interest_rate": [0.05], "years": [10, 20, 30]}}->{"calculate_present_value_1": {"payment_per_year": [1000], "interest_rate": [0.05], "years": [20]},"calculate_present_value_2": {"payment_per_year": [1000], "interest_rate": [0.05], "years": [30]}}Stacking upon this PR, this addresses 2 issues in
parallel_functionandparallel_multiple_functiontest category:This PR fix the parallel function possible answer. A checker rerun is required before merging this PR.Leaderboard PR should be merge at the same time.