Fix use_parallel_residual and qkv_bias for StableLM GGUF config extraction#34450
Fix use_parallel_residual and qkv_bias for StableLM GGUF config extraction#34450SunMarc merged 3 commits intohuggingface:mainfrom
use_parallel_residual and qkv_bias for StableLM GGUF config extraction#34450Conversation
|
Hey @Isotr0py! These changes are good to me. Thank you! Please, fix test_stablelm_weights_conversion_fp16 and test_stablelm_fp16 in test_ggml.py as well to get rid of config=original_model.config as we do not need it anymore |
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
|
Can you try to rebase your PR in order to pass the CI @Isotr0py ? |
|
@SunMarc I have merged the main branch but seems that the test CI is still failing in unrelated tests: |
Hey, try to do rebase. First of all, in command line, |
79a8774 to
3917d3d
Compare
|
The problematic test should have been fixed by #34605. Can you try to rebase on that ? |
803c278 to
a59795a
Compare
|
@SunMarc All tests passed now! |
|
Niceee ! |
…xtraction (huggingface#34450) * fix stablelm qkv_bias * fix stablelm qkv_bias and use_parallel_residual * remove original_model.config for stablelm gguf test
What does this PR do?
Fixes #34426 (issue)
Before submitting
Pull Request section?
to it if that's the case.
documentation guidelines, and
here are tips on formatting docstrings.
Who can review?
Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.
@VladOS95-cyber @SunMarc