Nikita Titov comments

Results 299 comments of


                                            Nikita Titov

[Discussion] efficiency improvements

@jameslamb Awesome proposal! Unfortunately, I'm not familiar with dask, but my intuition was that dask is about scaling training up to multiple machines. Something like "for small data use your...

[Discussion] efficiency improvements

@jameslamb Thanks a lot for the detailed response! > .that means that we can test against a dask.distributed.LocalCluster and have some confidence that it will work on a true multi-node...

feature request: Add parameter to control maximum group size for Lambdarank

I think we can turn that constant into parameter to not force users re-compile LightGBM. Although, I guess it's quite rare cases when users need to increase the default value.

[python-package] make `Dataset` pickleable

Indeed, `Dataset` object isn't serializable. `Booster` object (that is a trained LightGBM model actually, returned value of the `train()` function) is serializable because it can be re-created from the text...

Trainings binary logloss increasing in some iterations in voting-parallel setting

cc @shiyu1994

llama 70b takes 5.5 min to load on A100

Sorry for offtop. @rk-spirinova You'd better hide your public and unprotected ip from your screenshot.

Ollama stuck after few runs

@jmorganca Unfortunately, it isn't fixed in 0.1.25. OS: Ubuntu 22.04.2 LTS GPU: NVIDIA RTX A6000 (Driver Version: 530.41.03, CUDA Version: 12.1) Model: Tested `mixtral:8x7b-instruct-v0.1-q4_K_M`, `mixtral:8x7b-instruct-v0.1-q6_K`, `llama2:7b-chat-q4_0` Env: Official Docker `/api/generate`...