SORO Bedionita

Results 14 comments of SORO Bedionita

according to the paper all normal cell are the same so all normal cells have the same alphas. same for the reduction cells

thank you i downloaded all for tss approach

can you share your lora checkpoints? i also need the checkpoints for the base and large Roberta for a project. thank you

I have read this paper. what i can tell is that the greedy soup tests in a sequential way starting from the top best model if a model added to...

thank you for the prompt reaction. what i did was. 1- python scripts/train_few_shot.py [...] perfectly executed with no problem My confusion was in the argument parse configuration parameters list: for...

I ran your command and this is what i got | Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr| |----------------------------|-------|------|-----:|--------|---|-----:|---|-----:| |leaderboard_gpqa | N/A| | | | | | | | |...

thank you for your answer. i used this command. `lm_eval --model hf \ --model_args pretrained=google/gemma-3-4b-it\ --tasks winogrande\ --device "cuda:0" \ --num_fewshot 5\ --apply_chat_template\ --batch_size 4 \ --fewshot_as_multiturn` and got error...

aha yes i figured out. but it has been a while i do not remember what i did unless i look into it again. are you still having that problem?

thank you. i checked the leader board they use 0.4.2 as today. That link you share seem to from version 0.4.3