Skip to content

Allow model_max_tokens to be set to whatever the LLM maximum is #1233

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.

Sign up for GitHub

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

Jump to bottom
Open
iuliaturc opened this issue Feb 1, 2025 · 4 comments · May be fixed by #1631
Open

Allow model_max_tokens to be set to whatever the LLM maximum is #1233

iuliaturc opened this issue Feb 1, 2025 · 4 comments · May be fixed by #1631

Comments

@iuliaturc
Copy link

Description

I'm trying to use GenerateREADME and maximize the underlying LLM's context window. But unfortunately I can't figure out easily what that magical value is, because model_max_tokens isn't the length of the final input sent to the LLM.

For instance, I'm trying to consume the entire 128k context window. And I'm doing a bunch of trials:

  1. patchwork GenerateREADME ... model_max_tokens=128_000 ===> Error code: 400 - {'error': {'message': "This model's maximum context length is 128000 tokens. However, you requested 255511 tokens
  2. patchwork GenerateREADME ... model_max_tokens=64_000 ===> Error code: 400 - {'error': {'message': "This model's maximum context length is 128000 tokens. However, you requested 191511 tokens
  3. patchwork GenerateREADME ... model_max_tokens=30_000 ===> Error code: 400 - {'error': {'message': "This model's maximum context length is 128000 tokens. However, you requested 157511 tokens

So I need to keep guessing.

Proposed solution

Have an option to e.g. set model_max_tokens=-1, which would mean the maximum window allowed by the underlying LLM, once all the other tokens you're sending under the hood are accounted for.

Alternatives considered

n/a
@iuliaturc iuliaturc mentioned this issue Feb 1, 2025
Open
@iuliaturc
Copy link
Author

iuliaturc commented Feb 1, 2025 •
edited
Loading

Uhm silly me I could have just calculated the extra token count is 255k - 128k = 127k to realize that the maximum I can set model_max_tokens is 1k. But anyway, would still be nice to have something like model_max_tokens=-1 to not have to go through a failure and then do the calculation.

@iuliaturc
Copy link
Author

Which also makes me realize that passing the entirety of the codebase to the LLM (which I think is what code2prompt is doing) will eat up most tokens so you can't really get good documentation in 128k tokens. End of rant :)

@patched-admin
Copy link
Contributor

@iuliaturc I would recommed using the Gemini models for this patchflow. But we'll take a look at the tokens too! The template patchflow was meant to be a naive implementation - we do have some avenues to compress the code2prompt output.

@iuliaturc
Copy link
Author

@iuliaturc I would recommed using the Gemini models for this patchflow. But we'll take a look at the tokens too! The template patchflow was meant to be a naive implementation - we do have some avenues to compress the code2prompt output.

Nice, do you have any docs or official recommendations on how to compress the code2prompt output?

@patched-codes patched-codes bot linked a pull request Apr 14, 2025 that will close this issue
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Enhance Functionality: Allow Full LLM Max Tokens patched-codes/patchwork
2 participants
@iuliaturc @patched-admin