simonepri / lm-scorer

📃Language Model based sentences scoring library

simonepri/lm-scorer Issues

ValueError: Unable to create tensor, you should probably activate truncation and/or padding with 'padding=True' 'truncation=True' to have batched tensors with the same length. Perhaps your features (`input_ids` in this case) have excessive nesting (inputs type `list` where type `int` is expected).
Updated 2 years ago
Support for Python 3.8
Updated 2 years ago
Can't load config for 'gpt2'
Updated 3 years ago5
Python 3.8 support?
Updated 3 years ago5
Unable to run lm-scorer
Closed 4 years ago1
Support for AutoModelWithLMHead
Updated 3 years ago
Not really correct to include <|endoftext|> token in scoring?
Updated 3 years ago
couldn't load pretrained gpt2
Closed 4 years ago3
AH01215: OSError: Couldn't reach server at 'https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-config.json' to download pretrained model configuration file
Closed 4 years ago6
Couple of queries: 1) Fine tuned GPT2 2) BPE Encoding
Closed 4 years ago2
Possible missing words
Closed 4 years ago1