Creates an `input_fn` closure to be passed to Estimator.

Loads a fragment

Loads a vocabulary file into a dictionary.

Return pointer to first non-whitespace char in given string. */

Helper function to pad a tensor in the time dimension and retain the static depth dimension.

Helper function to pad a tensor in the time dimension and retain the static depth dimension.

Helper function to pad a tensor in the time dimension and retain the static depth dimension.

Position-wise Feed-forward Network.

Uses a confusion matrix to compute precision, recall and fbeta

Print summary of all quantizer modules in the model.

Print summary of all quantizer modules in the model.

Read a SQuAD json file into a list of SquadExample.

Reshapes a rank 2 tensor back to its original rank >= 2 tensor.

inputs: logits: [batch_size, vocab_size], the values of log logits threshold: int when using top_k, and a probabi

Save Bloom model configuration. Args: model_config: HF pretrained model configuration. save_dir: a directory to save the config

Set attributes for mod.quantizer.

Set attributes for mod.quantizer.

Set attributes for mod.quantizer.

Set quantizer attributes for layers where name contains a substring in names.

Set quantizer attributes for layers where name contains a substring in names.

Set quantizer attributes for layers where name contains a substring in names.

Split a full s3 path into the bucket name and path.

Version of strncpy that ensures dest (size bytes) is null-terminated. */

Run the bert transformer layer by TensorFlow. Args: inputs: A tf.Tensor with shape [batch_size, seq_len, hidden_dimension].