transfer-learning-conv-ai
transfer-learning-conv-ai copied to clipboard
🦄 State-of-the-Art Conversational AI with Transfer Learning
Should I expect to need to make any modifications to the training srcipt if my data has a lot of terms that would not be part of the GPT vocabulary?...
When I run the following command "python train.py --model="gpt2"" I keep getting the following error. INFO:transformers.modeling_utils:loading weights file https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-pytorch_model.bin from cache at None Traceback (most recent call last): File "/home/haskari/.local/lib/python3.9/site-packages/torch/serialization.py",...
RUnning the interact.py works with CLI inputs. Has anyone tried to access it as an API call to get a response?
GPT2 custom chat-bot single interaction. I am not using any thread in this implementation but still it says 'multiprocessing_chunksize'. Here we try to build chatbot using gpt2 and interact with...
Hi All, I am trying to train with sample set. python ./train.py --dataset_path=sample.json data input like as below getting below error File "./train.py", line 43, in pad_dataset max_l = max(len(x)...
Problem i faced : When i run interact.py to interact with my bot , there is no option to exit from interaction with bot or stop talking with bot. Solved...
I ran into some strange problems and want to share my solution here. When I ran the training script it did not use the GPUs. Another problem was that distributed...
Hi, I'm currently trying to build the docker image on AWS EC2 and this error keeps popping up: `Error processing tar file(exit status 1): write /usr/local/lib/python3.6/dist-packages/spacy/training/example.cpython-36m-x86_64-linux-gnu.so: no space left on...
Hi, In your paper, you said the "next-utterance classification" task and "language modeling" task were trained in a multi-task learning setting, and also in train.py, there is a function load...
Hi, Has anyone managed to train without persona taking into account only the context information?