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

contrib to knowledge sports cricket section #1232

Closed
wants to merge 2 commits into from

Conversation

nvaibhav
Copy link

@nvaibhav nvaibhav commented Jul 12, 2024

If your PR is related to a contribution to the taxonomy, please, fill
out the following questionnaire. If not, replace this whole text and the
following questionnaire with whatever information is applicable to your PR.

Describe the contribution to the taxonomy
The content that I want to contribute is to the knowledge of taxonomy.
I have added cricket in the sports/ and a qna.yaml and attribution files.
also
I have added Maximo IBM Product related knowledge in ..knowledge/software/products/Maximo
Below are details of both the submissions :
1.
While working on instructlab , I downloaded the existing model and asked question -
Who won the 1987 cricket world cup ?
Ans: Yes, India did win the 1987 World Cup, which was the 50-over format of the Cricket World Cup tournament. India defeated the West Indies in the final match to │
│ claim victory. This marked their first World Cup title in cricket after several attempts.
It gave me wrong answer(above), since the information on wikipedia said otherwise.

Later I created qna file and fed in correct information, generated synthetic data, trained the model and tested again.
I asked the question , this time it gave me correct answer.

  • Corrected answer to 1987 cricket world cup winner.
  • Gave inputs from wikipedia.
  • Got correct information about hosting of this year world cup.

Input given at the prompt

   Did India win the 1987 world cup ?

Response from the original model

    Yes, India did win the 1987 World Cup, which was the 50-over format of the Cricket World Cup tournament. India defeated the West Indies in the final match to claim victory. This marked their first World Cup title in cricket after several attempts.

Response from the fine-tuned model

  India did not win any matches in the 1987 cricket world cup, which was held in India and Pakistan.

After training the model, I asked bunch of questions, to which all the answers were correcrt.
Below are some of the questions I tried -

  1. Who won the 1987 cricket world cup ?
    Ans:Australia won the championship match against England by 7 runs, securing victory with just 23 balls left to spare.

  2. Did India won the 1987 cricket world cup ?
    Ans:No, India did not win the championship in 1987. They were knocked out during the group stage and finished in sixth place overall

  3. Did Australia won the 1987 world cup ?
    Ans: Australia won the championship match against England by a margin of just 7 runs, with both teams putting up an exceptional fight that came down to the final overs.

  4. Who hosted the 1987 cricket world cup ?
    Ans: India and Pakistan jointly hosted the 1987 tournament, marking the first time that the event was held outside England.

  5. IBM Maximo Product
    A query related to security template , and how this feature can be used to give access to any application. The meaning of it and the usage. Will help the customers understand and resolve authourization issues by themselves,.
    Questions like -
    What is a security template in Maximo ?
    How does security template work ?
    How do I give myself access to a application using a security template in Maximo ?
    Why to use a security template in Maximo ?
    I can't see the application menu, how can a security template fix it ?
    When should the security template be used in Maximo ?
    were used as examples and fed to the model.

Contribution checklist

  • The contribution was tested with ilab generate
  • No errors or warnings were produced by ilab generate
  • All commits are signed off (DCO)
  • The qna.yaml file contains at least 5 seed_examples
  • The qna.yaml file was linted and prettified (yaml-validator can do both)
  • An attribution.txt file in the same folder as the qna.yaml file
  • Content does not include PII or otherwise sensitive or confidential information
  • Content does not include anything documented in the project's Avoid these Topics guidelines

@github-actions github-actions bot added triage-needed (Auto labeled) skill is ready to be triaged knowledge (Auto labeled) labels Jul 12, 2024
Copy link

Beep, boop 🤖, Hi, I'm @instructlab-bot and I'm going to help you with your pull request. Thanks for you contribution! 🎉

I support the following commands:

  • @instructlab-bot precheck -- Check existing model behavior using the questions in this proposed change.
  • @instructlab-bot generate -- Generate a sample of synthetic data using the synthetic data generation backend infrastructure.
  • @instructlab-bot generate-local -- Generate a sample of synthetic data using a local model.
  • @instructlab-bot help -- Print this help message again.

Note

Results or Errors of these commands will be posted as a pull request check in the Checks section below

Note

Currently only maintainers belongs to [[taxonomy-triagers taxonomy-approvers taxonomy-maintainers labrador-org-maintainers instruct-lab-bot-maintainers]] teams are allowed to run these commands.

@jjasghar jjasghar added triage-requested-changes skill has been reviewed; changes requested from contributor and removed triage-needed (Auto labeled) skill is ready to be triaged labels Jul 12, 2024
@github-actions github-actions bot added the triage-needed (Auto labeled) skill is ready to be triaged label Jul 16, 2024
Copy link

Beep, boop 🤖, Hi, I'm @instructlab-bot and I'm going to help you with your pull request. Thanks for you contribution! 🎉

I support the following commands:

  • @instructlab-bot precheck -- Check existing model behavior using the questions in this proposed change.
  • @instructlab-bot generate -- Generate a sample of synthetic data using the synthetic data generation backend infrastructure.
  • @instructlab-bot generate-local -- Generate a sample of synthetic data using a local model.
  • @instructlab-bot help -- Print this help message again.

Note

Results or Errors of these commands will be posted as a pull request check in the Checks section below

Note

Currently only maintainers belongs to [[taxonomy-triagers taxonomy-approvers taxonomy-maintainers labrador-org-maintainers instruct-lab-bot-maintainers]] teams are allowed to run these commands.

Copy link
Member

@jjasghar jjasghar left a comment

Choose a reason for hiding this comment

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

Pleas remove the Maximo portions, and fix up the cricket questions, and the DCO of this PR.

@@ -0,0 +1,31 @@
version: 1
Copy link
Member

Choose a reason for hiding this comment

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

Please change this to version: 2

@@ -0,0 +1,4 @@
Title of work: Maximo application Authorization
Link to work: https://www.ibm.com/docs/en/mas-cd/maximo-manage/continuous-delivery?topic=groups-application-templates
License of the work: ABCD
Copy link
Member

Choose a reason for hiding this comment

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

This needs to be the correct wording.

@@ -0,0 +1,4 @@
Title of work: Maximo application Authorization
Copy link
Member

Choose a reason for hiding this comment

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

The PR title and this is different.

@@ -0,0 +1,4 @@
Title of work: Maximo application Authorization
Link to work: https://www.ibm.com/docs/en/mas-cd/maximo-manage/continuous-delivery?topic=groups-application-templates
Copy link
Member

Choose a reason for hiding this comment

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

We can not accept things that aren't in our approved list for the upstream model.

@@ -0,0 +1,16 @@
version: 1
Copy link
Member

Choose a reason for hiding this comment

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

Please change this to the version: 2

created_by: vainakil
domain: cricket_world
seed_examples:
- question: Who won the cricket 1987 world cup ?
Copy link
Member

Choose a reason for hiding this comment

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

There needs to be at least 5 questions.

India hosted the world cup however didn't win it. Australia won it.
document:
repo: https://github.com/nvaibhav/cricket
commit: 199f994
Copy link
Member

Choose a reason for hiding this comment

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

This needs to be the complete SHA.

@jjasghar jjasghar removed the triage-needed (Auto labeled) skill is ready to be triaged label Jul 16, 2024
answer: |
India hosted the world cup however didn't win it. Australia won it.
document:
repo: https://github.com/nvaibhav/cricket
Copy link
Member

Choose a reason for hiding this comment

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

This also is not the complete file, this needs to be the complete file from wikipedia to be considered to be upstreamed.

Copy link

github-actions bot commented Aug 1, 2024

This pull request has been automatically marked as stale because it has not had activity within 15 days. It will be automatically closed if no further activity occurs within 31 days.

@github-actions github-actions bot added the stale stale-bot has marked you as stale label Aug 1, 2024
@jjasghar
Copy link
Member

Hi! 👋
With the new update and release of 0.18.0, our base knowledge submissions have drastically changed. This has given us an opportunity to significantly improve the accuracy of our fine-tuned models, which is a major win for our community!

But alas, that has caused some changes that this PR isn't able to continue forward. We greatly appreciate the work you've put into this, and wish we could accept it but the amount of work to get it to be version: 3 is unrealistic for us to ask.
If you do want to do this, please don't hesitate to take the qna.yaml update it, and build it out. Otherwise, we hope you come back to our community with a new submission and help build out our Open Source community-driven LLM.

If you have any questions directly, please don't hesitate to comment on the PR or email me at awesomeATinstructlab.ai (yes, really), and I'll do my best to answer your questions.

@jjasghar jjasghar closed this Aug 20, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
knowledge (Auto labeled) stale stale-bot has marked you as stale triage-requested-changes skill has been reviewed; changes requested from contributor
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants