world2vec comments

Results 9 comments of


                                            world2vec

Redirecting stderr of SC2 process

Yes, it is really annoying. For me , I just want to hide all output from SC2 proc and keep output of my program. Do not how to do this!!!

score not right

@flyboyer Is your score on validate or test dataset? How about Model2?

implementation questions

Thanks for your quick response and guidance. Looking forward to your paper to know the gains of these 2 component. The first run of my implementation only have about 90.x...

Architecture for word-level Penn Treebank dataset

Dear authors, Could you publish details of model super parameters for PTB word? Thanks

Remove a cell from evaluation queue

Any update? lots of people want it!

For my training code(I did not use huggingface trainer), ``` model, tokenizer = FastLanguageModel.from_pretrained("xxxx", dtype=getattr(torch, 'bfloat16'), max_seq_length=768, load_in_4bit=True) model = FastLanguageModel.get_peft_model(model, r=64, lora_alpha=16, lora_dropout=0, bias="none", random_state=32 target_modules=["q_proj", "k_proj", "v_proj", "o_proj",...

Lora downcasting issue

@danielhanchen For my case is on RTX4090. torch AMP with float16 work well, it does not work for bfloat16.

What is llmxmapreduce? Any reference?

Thanks!