-
Hello,
I am trying to finetune the tapas_wtq_wikisql_sqa_masklm_medium_reset.
Just to see, if it works in general, I wanted to finetune it on the same data it's already trained on, WTQ. Creating …
-
First of all, great job on the project! I was wondering if there were any implemented functionality to finetune this model? Basically introducing another dataset to train on top of the already trained…
-
Should finetune all TDBN or just CRBM+LogReg?
At the moment (13 avril 2016), I try to put together all my models.
In other words, until now I train RBMs and use them to generate a new dataset (train,…
-
**Describe the bug**
Related to the [issue](https://github.com/ACEsuit/mace/issues/615)
When I do Multihead transfer learning from a personal pre-trained model. I found that the `energy_key` and `fo…
-
When finetuning the model I will have to create a dataset of some episodes.
Do you have any resources on how you recorded/created a RLDS dataset? It seems to be somewhat niche with little documentat…
-
Hey guys,
I'm pretty new here just trying to figure all this out.
Finally managed to get my first finetuning running. But I'm kinda confused.
I'm using the thomas - medium model (german) for fine…
-
Thanks for your impressive work. But the dataset given in the Baidu disk doesn't fit the finetuning process. If I want to reprodce the results in your paper, should I download the official SUN RGB-D d…
-
Hi there,
First of all thanks for such an awesome work, I tried it for my custom usecase, it gave me awesome results.
But only 2 classes are missing, I also tried using different custom labels, as t…
-
Trying to use `generate_qa_embedding_pairs` method to create synthetic data.
`from llama_index.finetuning import generate_qa_embedding_pairs`
I run into an error:
```
---------------------…
-
在finetune代码中,部分也加入了loss的计算,想请教下这样相比conditioning language modeling loss有什么特别的好处吗?