Unified tokenizer type onboarding

[srikary12]

Resolves #1536

Moves TokenizerType to a centralized place.

Adds support at different places.

To do

Add documentation for future tokenizer onboard

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/torchchat/1540

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

❌ 8 New Failures, 3 Cancelled Jobs

As of commit 22fdd56 with merge base 71552fd ():

NEW FAILURES - The following jobs have failed:

• pull / runner-aoti (macos-14-xlarge) (gh)
  Process completed with exit code 1.
• pull / runner-et (macos-14-xlarge) (gh)
  Process completed with exit code 1.
• pull / test-build-runner-et-android / linux-job (gh)
  RuntimeError: Command docker exec -t 9214b36d7c4eb5649d9bac39b5af7da9cfd9e286220c68cc9642b09afd9098f8 /exec failed with exit code 1
• pull / test-tinystories-executorch (macos-14-xlarge) (gh)
  Process completed with exit code 1.
• pull / test-torchao-experimental-cpp (macos-14-xlarge) (gh)
  Process completed with exit code 1.
• pull / test-torchao-experimental-et (macos-14-xlarge) (gh)
  Process completed with exit code 1.
• Run parallel prefill / test-sdpa-backends-export / linux-job (gh)
  RuntimeError: Command docker exec -t 6906f7bb7689649eb3ab05f6153c0f351c9f5b4d528ad192b8ecf2ff2ec818a6 /exec failed with exit code 1
• Run the aoti runner with CUDA using stories / test-runner-aot-cuda / linux-job (gh)
  RuntimeError: Command docker exec -t abfc46d5c1382824d2b37b692d54a247e7916d17a475160e4fb9885ecc66f351 /exec failed with exit code 1

CANCELLED JOBS - The following jobs were cancelled. Please retry:

• pull / runner-aoti (16-core-ubuntu) (gh)
  ##[error]The operation was canceled.
• pull / runner-et (16-core-ubuntu) (gh)
  ##[error]The operation was canceled.
• pull / test-tinystories-executorch (16-core-ubuntu) (gh)
  ##[error]The operation was canceled.

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[facebook-github-bot]

Hi @srikary12!

Thank you for your pull request and welcome to our community.

Action Required

In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at [email protected]. Thanks!

[facebook-github-bot]

Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks!

[zhenyan-zhang-meta]

Thanks for the contribution!

Some comments in general:

• We haven't touched

  torchchat/dist_run.py

  Lines 67 to 69 in 0299a37

  	class TokenizerType(Enum):
  	Tiktoken = auto()
  	SentencePiece = auto()

  yet, can we use your newly created enum class there as well?
• I've helped to run tests python torchchat.py generate llama2|llama3|granite-code and it works. The CI might have some issue in the previous run or it might be from merge conflicts. I've resolved the conflicts but in case if there's still CI issue we might need to take a look. cc @Jack-Khuu

[zhenyan-zhang-meta]

cc @Jack-Khuu for a review as well.

[srikary12]

@zhenyan-zhang-meta I've modified dist_run.py and resolved conversations.

[srikary12]

I'll fix test cases. Looks like I missed some comparisons.

[srikary12]

@zhenyan-zhang-meta I've checked all the cases. Let me know if I am missing something.

[zhenyan-zhang-meta]

@srikary12 I think overall it looks fine, thanks for the contribution! Just turned on the CI for some extra checks.

Meanwhile if you could update the doc it would be great.

[srikary12]

@zhenyan-zhang-meta we might need to check CI/CD. Not sure if I am missing something. I'll try to add documentation asap.