Update compression config for openlm-research/open_llama_3b_v2

[nikita-savelyevv]

Reduce PPL for compressed openlm-research/open_llama_3b_v2 by removing all_layers=True and adding AWQ.

Precision	all_layers	AWQ	PPL
FP16			12.40
INT4_SYM	False	False	13.45
INT4_SYM	True	False	13.73
INT4_ASYM	False	True	12.77
INT4_ASYM	False	False	13.15
INT4_ASYM	True	False	13.36

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests?

[nikita-savelyevv]

@KodiaqQ please take a look

[KodiaqQ]

@nikita-savelyevv, you've provided numbers in the description with the ASYM mode, while configuration contains "sym": True. Why so?

[nikita-savelyevv]

@KodiaqQ Thanks for noticing. There were some errors in the collected metrics. I've updated the metrics in the PR description and changed the mode to asymmetric.

[HuggingFaceDocBuilderDev]

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.