Need help with Elmo-Tutorial?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

149 Stars 37 Forks 27 Commits 0 Opened issues


A short tutorial on Elmo training (Pre trained, Training on new data, Incremental training)

Services available


Need anything else?

Contributors list

# 193,652
22 commits
# 268,763
1 commit


This is a short tutorial on using Deep contextualized word representations (ELMo) which is discussed in the paper This tutorial can help in using:

  • Pre Trained Elmo Model - refer Elmotutorial.ipynb_
  • Training an Elmo Model on your new data from scratch

To train and evaluate a biLM, you need to provide: * a vocabulary file * a set of training files * a set of heldout files

The vocabulary file is a text file with one token per line. It must also include the special tokens , and The vocabulary file should be sorted in descending order by token count in your training data. The first three entries/lines should be the special tokens :


The training data should be randomly split into many training files, each containing one slice of the data. Each file contains pre-tokenized and white space separated text, one sentence per line.

Don't include the

 tokens in your training data.

Once done, git clone and run:

python bin/ --train_prefix=  --vocab_file  --save_dir 

To get the weights file, run:

python bin/ --save_dir /output_path/to/checkpoint --outfile/output_path/to/weights.hdf5

In the save dir, one options.json will be dumped and above command will give you a weights file required to create an Elmo model (options file and the weights file)

For more information refer Elmo_tutorial.ipynb

  • ## Incremental Learning/Training

To incrementally train an existing model with new data

While doing Incremental training : git clone

Once done, replace trainelmo_ within allenai/bilm-tf/bin/ with provided at home.

Updated changes :

tf_save_dir = args.save_dir
tf_log_dir = args.save_dir
train(options, data, n_gpus, tf_save_dir, tf_log_dir,restart_ckpt_file)

if name == 'main': parser = argparse.ArgumentParser() parser.add_argument('--save_dir', help='Location of checkpoint files') parser.add_argument('--vocab_file', help='Vocabulary file') parser.add_argument('--train_prefix', help='Prefix for train files') parser.add_argument('--restart_ckpt_file', help='latest checkpoint file to start with')

This takes an argument (--restartckptfile) to accept the path of the checkpointed file.

replace within allenai/bilm-tf/bilm/ with provided at home. Also, make sure to put your embedding layer name in line 758 in :

exclude = ['the embedding layer name you want to remove']

Updated changes :


    # load the checkpoint data if needed
    if restart_ckpt_file is not None:
        reader = tf.train.NewCheckpointReader(your_checkpoint_file)
        cur_vars = reader.get_variable_to_shape_map()
        exclude = ['the embedding layer name you want to remove']
        variables_to_restore = tf.contrib.slim.get_variables_to_restore(exclude=exclude)
        loader = tf.train.Saver(variables_to_restore)
        #loader = tf.train.Saver(),'/tmp')
        loader.restore(sess, '/tmp')
        with open(os.path.join(tf_save_dir, 'options.json'), 'w') as fout:

summary_writer = tf.summary.FileWriter(tf_log_dir, sess.graph)

The code reads the checkpointed file and reads all the current variables in the graph and excludes the layers mentioned in the exclude variable, restores rest of the variables along with the associated weights.

For training run:

 python bin/ --train_prefix=  --vocab_file  --save_dir  --restart_ckpt_file 

In the within bin, set these options based on your data:

batch_size = 128  # batch size for each GPU
n_gpus = 3

number of tokens in training data

n_train_tokens =

options = { 'bidirectional': True, 'dropout': 0.1, 'all_clip_norm_val': 10.0,

'n_epochs': 10, 'n_train_tokens': n_train_tokens, 'batch_size': batch_size, 'n_tokens_vocab': vocab.size, 'unroll_steps': 20, 'n_negative_samples_batch': 8192,


Visualization of the word vectors using Elmo:

  • Tsne Optional Text

  • Tensorboard

Optional Text

Using Elmo Embedding layer in consequent models

if you want to use Elmo Embedding layer in consequent model build refer :

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.