DialoGPT
DialoGPT copied to clipboard
microsoft
Large-scale pretraining for dialogue
Thank you for your contribution. I noticed a few things about your repo: - Variable names are vague and uninformative, which makes it hard to understand the code and adapt...
I'm using a modified version of the example code provided in the huggingface website. ```py from transformers import AutoModelForCausalLM, AutoTokenizer import torch tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-medium") model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-medium") step =...
Hi, there, hope you have a good day. When I compile the demo.py --data full, I had makefile error. I'm wondering if anyone could help me to take a look?...
Hello. I fine tuned my DialoGPT small model and trained it on Daily Dialogue database. When speaking with the model, on its last utterance generation, the outputs has random punctuation...
 Hello, I made the above mistake when EXECUTING A. I hope I can get the answer
I have tried to implement DialoGPT using this code ``` # encode the new user input, add the eos_token and return a tensor in Pytorch new_user_input_ids = tokenizer.encode(input(genpromptfinal) + tokenizer.eos_token,...
Hello, The link included in the README for `mteval-v14c.pl` is broken. I obtained the same results as Yu-An (Issue #48) by using moses-smt [mteval-v14.pl ](https://github.com/moses-smt/mosesdecoder/blob/master/scripts/generic/mteval-v14.pl). NIST is a lot lower...
I am trying to convert the DialogGPT model to Torchscript to load the model into [Triton](https://github.com/triton-inference-server/server). I tried to use JIT to trace the model as mentioned [here](https://huggingface.co/docs/transformers/master/serialization#torchscript) but hitting...
Hi, I want to evaluate the pre-trained dialoGPT . I followed the guidance in README, but I cannot get the "data-official-test/test.refs.txt" following:"Please follow the DSTC-7 official repo to extract the...
