-
Thank you for your great work and swift answers. Maybe LoNAS (or LLaMA-NAS) can bring one-shot NAS back to the era of LLMs.
I noticed that in `run_glue.py`, when we set the flag `do_search=True`, …
-
Hi there, thanks for your work! I want to inquire about the source of the commonsense_15k dataset, as I didn't find it in the paper nor described in this repo.
-
您好,我看到论文中展示了在commonsense_qa和openbook_qa上的微调效果,请问能否提供这两个数据集的preparation和evaluation代码,谢谢。
-
When I'm doing the evaluation, should I use _--load_8bit_? I'm trying to reproduce the results of LLaMa-7B-LoRA
Finetune:
`CUDA_VISIBLE_DEVICES=8 python finetune.py --base_model 'yahma/llama-7b-…
-
```
pybullet build time: May 16 2024 23:57:18
WARNING - 2024-05-17 02:28:39,256 - rigid_transformations - Failed to import geometry msgs in rigid_transformations.py.
WARNING - 2024-05-17 02:28:39,2…
-
Hi, I am trying to finetune llama on commonsense_170k. However, I find the when the loss value is around 0.6, it almost does not decrease. Is it normal?
` WORLD_SIZE=2 CUDA_VISIBLE_DEVICES=1,2,3,4 …
-
Based on the idea of https://github.com/Watts-Lab/Commonsense-Platform/issues/61, we want to conduct an integrative experiment across statement design points. Here we outline the experiment and a regi…
-
https://arxiv.org/pdf/2403.07398.pdf
-
https://github.com/adapt-sjtu/commonsense-locatednear
-
We'll try a slightly different format for our meeting notes this summer, and keep them all in a single thread. This is it!