convert : Qwerky : use lora_rank_tokenshift and lora_rank_decay if present #12667
Conversation
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
|
The change looks good to me. I haven't got the chance to download the full 72B model yet. Have you tested this? |
|
@MollySophia No, purely based on diffing the modeling code. |
I see. Then let's wait for a feedback from #12662 :) |
|
BTW, the QWQ-32B modeling code uses ref: |
|
@MollySophia Looks like it's working, even though @kanttouchthis only tested 32B I think it's safe to assume this change works for 72B too. |
MollySophia
approved these changes
Mar 31, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
The config items
lora_rank_tokenshiftandlora_rank_decaywere introduced in new release, see:https://huggingface.co/featherless-ai/Qwerky-72B/blob/main/modeling_rwkv6qwen2.py#L268-L279
Fixes #12662