Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

added Phi-3 handlers #640

Merged
merged 8 commits into from
Sep 29, 2024
Merged

Conversation

AndyChenYH
Copy link
Contributor

Added handler for:
phi-3-mini-4k-instruct
phi-3-mini-128k-instruct
phi-3-small-8k-instruct
phi-3-small-128k-instruct
phi-3-medium-4,-instruct
phi-3-medium-128k-instruct
phi-3.5-mini-instruct

Rank Model Model Link Organization License AST Summary Simple AST Multiple AST Parallel AST Parallel Multiple AST Irrelevance Detection Relevance Detection
1 Phi-3-small-8k-instruct (Prompt) https://huggingface.co/microsoft/Phi-3-small-8k-instruct Microsoft MIT 66.39% 59.70% 64.20% 76.75% 64.92% 47.06% 87.80%
2 Phi-3-medium-4k-instruct (Prompt) https://huggingface.co/microsoft/Phi-3-medium-4k-instruct Microsoft MIT 62.10% 66.67% 67.40% 62.00% 52.33% 46.79% 78.05%
3 Phi-3-mini-4k-instruct (Prompt) https://huggingface.co/microsoft/Phi-3-mini-4k-instruct Microsoft MIT 66.63% 70.76% 75.67% 69.75% 50.33% 20.25% 75.61%
4 Phi-3.5-mini-instruct (Prompt) https://huggingface.co/microsoft/Phi-3.5-mini-instruct Microsoft MIT 55.13% 64.22% 66.12% 52.00% 38.17% 64.93% 70.73%
5 Phi-3-mini-128k-instruct (Prompt) https://huggingface.co/microsoft/Phi-3-mini-128k-instruct Microsoft MIT 51.49% 67.60% 72.50% 41.12% 24.75% 44.07% 85.37%

@HuanzhiMao
Copy link
Collaborator

Also, Phi-3-mini, Phi-3-small, Phi-3-medium, and Phi-3.5 all have different chat templates. So you need different _format_prompt functions.

Copy link
Collaborator

@HuanzhiMao HuanzhiMao left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

Copy link
Owner

@ShishirPatil ShishirPatil left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you @AndyChenYH and congratulations on landing your first PR!

@ShishirPatil ShishirPatil merged commit 37f61bf into ShishirPatil:main Sep 29, 2024
dyang415 pushed a commit to empower-ai/gorilla that referenced this pull request Sep 30, 2024
Added handler for:
phi-3-mini-4k-instruct
phi-3-mini-128k-instruct
phi-3-small-8k-instruct
phi-3-small-128k-instruct
phi-3-medium-4,-instruct
phi-3-medium-128k-instruct
phi-3.5-mini-instruct

|Rank|Model |Model Link |Organization|License |AST Summary|Simple
AST|Multiple AST|Parallel AST|Parallel Multiple AST|Irrelevance
Detection|Relevance Detection|

|----|---------------------------------|---------------------------------------------------------|------------|------------|-----------|----------|------------|------------|---------------------|---------------------|-------------------|
|1 |Phi-3-small-8k-instruct (Prompt)
|https://huggingface.co/microsoft/Phi-3-small-8k-instruct |Microsoft
|MIT |66.39% |59.70% |64.20% |76.75% |64.92% |47.06% |87.80% |
|2 |Phi-3-medium-4k-instruct
(Prompt)|https://huggingface.co/microsoft/Phi-3-medium-4k-instruct|Microsoft
|MIT |62.10% |66.67% |67.40% |62.00% |52.33% |46.79% |78.05% |
|3 |Phi-3-mini-4k-instruct (Prompt)
|https://huggingface.co/microsoft/Phi-3-mini-4k-instruct |Microsoft |MIT
|66.63% |70.76% |75.67% |69.75% |50.33% |20.25% |75.61% |
|4 |Phi-3.5-mini-instruct (Prompt)
|https://huggingface.co/microsoft/Phi-3.5-mini-instruct |Microsoft |MIT
|55.13% |64.22% |66.12% |52.00% |38.17% |64.93% |70.73% |
|5 |Phi-3-mini-128k-instruct
(Prompt)|https://huggingface.co/microsoft/Phi-3-mini-128k-instruct|Microsoft
|MIT |51.49% |67.60% |72.50% |41.12% |24.75% |44.07% |85.37% |

---------

Co-authored-by: Huanzhi (Hans) Mao <[email protected]>
ShishirPatil pushed a commit that referenced this pull request Oct 21, 2024
This PR updates the leaderboard to reflect the change in score due to
the following PR merge:

1. #660 
2. #661
3. #683
4. #679
5. #708 
6. #709
7. #701
8. #657 
9. #658 
10. #640 
11. #653
12. #642 
13. #696 
14. #667

Close #662.

Note: Some models (like `firefunction`, `functionary`,
`microsoft/phi`)are not included in this leaderboard update because we
don't have all the entries generated. We will add them back once we get
the full result generated.
VishnuSuresh27 pushed a commit to VishnuSuresh27/gorilla that referenced this pull request Nov 11, 2024
Added handler for:
phi-3-mini-4k-instruct
phi-3-mini-128k-instruct
phi-3-small-8k-instruct
phi-3-small-128k-instruct
phi-3-medium-4,-instruct
phi-3-medium-128k-instruct
phi-3.5-mini-instruct

|Rank|Model |Model Link |Organization|License |AST Summary|Simple
AST|Multiple AST|Parallel AST|Parallel Multiple AST|Irrelevance
Detection|Relevance Detection|

|----|---------------------------------|---------------------------------------------------------|------------|------------|-----------|----------|------------|------------|---------------------|---------------------|-------------------|
|1 |Phi-3-small-8k-instruct (Prompt)
|https://huggingface.co/microsoft/Phi-3-small-8k-instruct |Microsoft
|MIT |66.39% |59.70% |64.20% |76.75% |64.92% |47.06% |87.80% |
|2 |Phi-3-medium-4k-instruct
(Prompt)|https://huggingface.co/microsoft/Phi-3-medium-4k-instruct|Microsoft
|MIT |62.10% |66.67% |67.40% |62.00% |52.33% |46.79% |78.05% |
|3 |Phi-3-mini-4k-instruct (Prompt)
|https://huggingface.co/microsoft/Phi-3-mini-4k-instruct |Microsoft |MIT
|66.63% |70.76% |75.67% |69.75% |50.33% |20.25% |75.61% |
|4 |Phi-3.5-mini-instruct (Prompt)
|https://huggingface.co/microsoft/Phi-3.5-mini-instruct |Microsoft |MIT
|55.13% |64.22% |66.12% |52.00% |38.17% |64.93% |70.73% |
|5 |Phi-3-mini-128k-instruct
(Prompt)|https://huggingface.co/microsoft/Phi-3-mini-128k-instruct|Microsoft
|MIT |51.49% |67.60% |72.50% |41.12% |24.75% |44.07% |85.37% |

---------

Co-authored-by: Huanzhi (Hans) Mao <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants