transfer-learning-conv-ai
transfer-learning-conv-ai copied to clipboard
huggingface
🦄 State-of-the-Art Conversational AI with Transfer Learning
Hi there! I've trained my model and my server was down after the first epoch. How can I load the model checkpoint? When I run train.py I got the following...
Hello I'm pretty new to Pytorch so sorry if this question was so simple. Because of memory limits, I can't pad my dataset as a whole. So I was wondering...
I'm reading the code (Line 93 in train.py) for the parameter 'personality_permutations'. I'm wondering why we're doing this. Will this make the model perform more reliable? Can anyone provide some...
Hi! I meet some problems when running ConvAI2 evaluation scripts: I first trained a model from OpenAI GPT. I increased the number of cumulative gradients because I only have one...
For Line 63 of train.py, it seems that "sequence[0] = [[bos] + list(chain(*persona))]". In this case, sequence[0] will be assigned as _speaker1_ (i.e., the user), why is this?
Hello, This is with respect to the dataset file being used by the code here at https://s3.amazonaws.com/datasets.huggingface.co/personachat/personachat_self_original.json. Can anyone tell what the "candidate" utterances are? I could not find a...
The pre-trained and fine-tuned model, given in the README of the repo under the 'Pretrained model' heading (linked [here](https://s3.amazonaws.com/models.huggingface.co/transfer-learning-chatbot/finetuned_chatbot_gpt.tar.gz)) is different from what gets used when we run `python interact.py`....
If I don't have CUDA support, this code wouldn't work right, since you guys are using NVIDIA's apex which requires CUDA? Just wondering if there's an alternative?
https://github.com/huggingface/transfer-learning-conv-ai/issues/98
Metadata
Owner
Metadata
🦄 State-of-the-Art Conversational AI with Transfer Learning