-
ref: [https://scrapbox.io/sho-lab-scraps/2023-12-05_打ち合わせ](https://scrapbox.io/sho-lab-scraps/2023-12-05_%E6%89%93%E3%81%A1%E5%90%88%E3%82%8F%E3%81%9B)
# これまでに挙がった論文
- [x] 共感性尺度の再構成
- [x] 共感的態度を評価する…
-
I get this when i try to train the model :
Traceback (most recent call last):
File "train.py", line 88, in
trainset, data_loader_train = load_dataset('train', indexer, batch_size)
File…
-
您好 您的代码有数据吗 可以共享一下吗？
-
**Describe the bug**
When creating an agent, we associate a Core Memory persona and human. The association is created properly using the API. However, when the agent is deleted, the linked persona an…
-
The _user_id_ field is not working correctly when creating a new agent via the REST API. Regardless of the user_id provided in the request, the created agent always has _"user_id": "user-00000"_ in th…
-
I ran this command "!python /kaggle/working/DGSlow/attack.py --attack_strategy structure --model_name_or_path facebook/bart-base --dataset empathetic_dialogues --use_combined_loss --out_dir ketqua_att…
-
## Hidden Knowledge
When experimenting with various prompts, it becomes apparent that the models possess more knowledge than they initially reveal.
For instance, stating that the assistant is an…
-
I am trying to train a T5 model on empathetic dialogues. I am running into cuda OOM errors when training my model with the following command. When training the BlenderBot 3B model, I ran into this iss…
-
Hello,
I really like the idea to combine spacy with google stuff, thanks! I got some seemingly random deadlock problem...
I am basically doing n*(n-1)/2 comparison on 50K papers by their titles …
-
**Describe the bug**
过程是这样的：
通过hanlp.pretrained.ALL 取得了load在变量后进行批量load，发现出错很多：
**Code to reproduce the issue**
Provide a reproducible test case that is the bare minimum necessary to gene…