noise-field / russian-ulmfit Goto Github PK
View Code? Open in Web Editor NEWAWD-LSTM language model trained on newspaper corpora with fast.ai
AWD-LSTM language model trained on newspaper corpora with fast.ai
Dear author, could you please clarify what is the vocabulary size in your pretrained LMs? From the notebook, it seems that you leave only 60k most frequent words. However, from the files of your pretrained model, it seems that vocabulary is about 250k.
Good day!
I want to fine-tune your language model on my own data, however, I got a problem:
RuntimeError: Error(s) in loading state_dict for SequentialRNN:
size mismatch for 0.rnns.0.weight_hh_l0_raw: copying a param with shape torch.Size([4600, 1150]) from checkpoint, the shape in current model is torch.Size([4608, 1152]).
size mismatch for 0.rnns.0.module.weight_ih_l0: copying a param with shape torch.Size([4600, 400]) from checkpoint, the shape in current model is torch.Size([4608, 400]).
size mismatch for 0.rnns.0.module.weight_hh_l0: copying a param with shape torch.Size([4600, 1150]) from checkpoint, the shape in current model is torch.Size([4608, 1152]).
size mismatch for 0.rnns.0.module.bias_ih_l0: copying a param with shape torch.Size([4600]) from checkpoint, the shape in current model is torch.Size([4608]).
size mismatch for 0.rnns.0.module.bias_hh_l0: copying a param with shape torch.Size([4600]) from checkpoint, the shape in current model is torch.Size([4608]).
size mismatch for 0.rnns.1.weight_hh_l0_raw: copying a param with shape torch.Size([4600, 1150]) from checkpoint, the shape in current model is torch.Size([4608, 1152]).
size mismatch for 0.rnns.1.module.weight_ih_l0: copying a param with shape torch.Size([4600, 1150]) from checkpoint, the shape in current model is torch.Size([4608, 1152]).
size mismatch for 0.rnns.1.module.weight_hh_l0: copying a param with shape torch.Size([4600, 1150]) from checkpoint, the shape in current model is torch.Size([4608, 1152]).
size mismatch for 0.rnns.1.module.bias_ih_l0: copying a param with shape torch.Size([4600]) from checkpoint, the shape in current model is torch.Size([4608]).
size mismatch for 0.rnns.1.module.bias_hh_l0: copying a param with shape torch.Size([4600]) from checkpoint, the shape in current model is torch.Size([4608]).
size mismatch for 0.rnns.2.module.weight_ih_l0: copying a param with shape torch.Size([1600, 1150]) from checkpoint, the shape in current model is torch.Size([1600, 1152]).
What version of fast.ai did you use?
My code is:
learn = language_model_learner(
data_lm,
AWD_LSTM,
pretrained=False,
drop_mult=0.3,
pretrained_fnames=['lm_5_ep_lr2-3_5_stlr', 'itos']
)
Before that, I've changed config:
config = awd_lstm_lm_config.copy()
config['n_hid'] = 1150
My fast.ai version is 1.0.61
Thank you!
What is the FastAI version you used?
Thanks!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.