{ "

Auto regressive model

\n": "

\u81ea\u52a8\u56de\u5f52\u6a21\u578b

\n", "

Configurations

\n

The default configs can and will be over-ridden when we start the experiment

\n": "

\u914d\u7f6e

\n

\u5f53\u6211\u4eec\u5f00\u59cb\u5b9e\u9a8c\u65f6\uff0c\u9ed8\u8ba4\u914d\u7f6e\u53ef\u4ee5\u800c\u4e14\u5c06\u4f1a\u88ab\u8986\u76d6

\n", "

Initialize the auto-regressive model

\n": "

\u521d\u59cb\u5316\u81ea\u56de\u5f52\u6a21\u578b

\n", "

_^_0_^_

\n": "

_^_0_^_

\n", "

A dictionary of configurations to override

\n": "

\u8981\u8986\u76d6\u7684\u914d\u7f6e\u5b57\u5178

\n", "

Create configs

\n": "

\u521b\u5efa\u914d\u7f6e

\n", "

Create experiment

\n": "

\u521b\u5efa\u5b9e\u9a8c

\n", "

Embed the tokens (_^_0_^_) and run it through the the transformer

\n": "

\u5d4c\u5165\u4ee4\u724c (_^_0_^_) \u5e76\u901a\u8fc7\u53d8\u538b\u5668\u8fd0\u884c\u5b83

\n", "

Generate logits of the next token

\n": "

\u751f\u6210\u4e0b\u4e00\u4e2a\u4ee4\u724c\u7684\u65e5\u5fd7

\n", "

Load configurations

\n": "

\u88c5\u8f7d\u914d\u7f6e

\n", "

Set models for saving and loading

\n": "

\u8bbe\u7f6e\u7528\u4e8e\u4fdd\u5b58\u548c\u52a0\u8f7d\u7684\u6a21\u578b

\n", "

Start the experiment

\n": "

\u5f00\u59cb\u5b9e\u9a8c

\n", "

Token embedding module

\n": "

\u4ee4\u724c\u5d4c\u5165\u6a21\u5757

\n", "experiment.py": "experiment.py" }