andreyanufr

lambada-openai |   |   |   -- | -- | -- | -- model | precision | acc | ppl   |   |   |   stabilityai_stablelm-2-zephyr-1_6b | fp32 | 0.5925 | 6.3024 stabilityai_stablelm-2-zephyr-1_6b |...

We had some list of papers which we used, but I can not remember it. Some details you can find in https://github.com/openvinotoolkit/open_model_zoo/issues/3856

> @nikita-malininn @nikita-savelyevv @ljaljushkin @andreyanufr Guys, please have a look. It is still a raw version, but any feedback will be valuable. @andrey-churkin 1) Is tools/llm_weight_compression/config_optimum_lm_eval.json default configuarion ? May...

@alexsu52 post_training_weight_compression 82

> Do you have a verification that it correctly quantizes values to the specified codebook? @ljaljushkin I added test for verification.