server: add descriptions for rope/yarn settings#2305
Open
rumitvn wants to merge 1 commit into
Open
Conversation
The `rope_scaling_type` and `yarn_*` server settings had no `description=`, so they rendered blank in `python -m llama_cpp.server --help` and in the auto-generated server settings reference (cli.py forwards `field.description` to argparse `help=`). Fill in accurate descriptions. Addresses abetlen#635
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Addresses #635
The
rope_scaling_typeandyarn_*fields inllama_cpp/server/settings.pyhad nodescription=, so they showed up blank in both:python -m llama_cpp.server --help(argparse), andllama_cpp/server/cli.pyforwardsfield.descriptionstraight into argparsehelp=(add_args_from_model), so filling these in fixes the CLI help and the rendered docs in one change.Fields filled
rope_scaling_type,yarn_ext_factor,yarn_attn_factor,yarn_beta_fast,yarn_beta_slow,yarn_orig_ctx— wording mirrors llama.cpp's own RoPE/YaRN parameter help.No behavior change; metadata only.