todo.txt

# wrap up mmodel code

# Experiment with quantization and velocity

# join sequences from accompany

# evaluation
- log-> chart
- perplexity

# Generate examples

# Similarity plots


# Next steps Lakhnes
# Next steps listener tests
# Next steps velocity experimentation



# boilerplate for generate (file->file)

# Model CLI

# Pre train on lakh

# Listening test  

# README





# Ge rid of these errors
/opt/conda/conda-bld/pytorch_1587428091666/work/aten/src/ATen/native/cuda/LegacyDefinitions.cpp:19: UserWarning: masked_fill_ received a mask with dtype torch.uint8, this behavior is now deprecated,please use a mask with dtype torch.bool instead.

Warning: masked_fill_ received a mask with dtype torch.uint8, this behavior is now deprecated,please use a mask with dtype torch.bool instead. (masked_fill__cuda at /opt/conda/conda-bld/pytorch_1587428091666/work/aten/src/ATen/native/cuda/LegacyDefinitions.cpp:19)