-
pretrain使用的是maemodel模型，finetune使用的是vitmodel模型，我的理解对吧，如果是这样的话pretrain的模型怎么能够再次finetune呢？
-
congratulations on the great work!
U am Miquel, part of hugging face.
I would like to do some finetunings on top of your model but to ensure I am improving something I would like to evaluate again…
-
Dear author, I have used the pretrain_full.pt you provided to sequentially execute the finetune.sh and generate.sh scripts, and the results obtained are as follows. Is there anything wrong with the tr…
-
Hi. I have finetune the _Helsinki-NLP/opus-mt-zh-vi_ model for translating Chinese to Vietnamese. When I convert the model to ctranslate2, the performance is decrease (from 32 sacrebleu with transform…
-
Thanks for your great job！When will open source finetune code？
-
I am trying to build on your knn-transfomers [repo](https://github.com/neulab/knn-transformers/tree/master?tab=readme-ov-file).
When I run the distill gpt with the given setup in the repo but with …
-
Convert dataset to a single CSV with columns `seq` and `label`, where `label = H | I | C` for HIV, Influenza and COVID respectively.
Truncate each sequence to be 8k nucleotides long
-
我在用CosyVoice-300M+自己的数据 进行finetune合成样例时
1. finetune后的模型发现了许多发音错误, 而用BASE model进行推理就不会有这种发音错误，这样的原因是什么呢？我的数据抄本音频都是没问题的
2. 笑声停不下来，例如文本是：“...哈哈哈”，合成的音频是：“...哈哈哈哈哈哈...”，这样的现象是为什么呢
-
Thank you for your work. What are the detailed steps for the fourth step?
-
model: donut-base-finetuned-docvqa
firsr I got a mistake:" AttributeError: 'SwinTransformer' object has no attribute 'pos_drop'"
then I delete this line:
![image](https://github.com/clovaai/do…