-
hi author,
I noticed that your classifier_free_dropout is 0.2, but what is the reason for setting classifier_scale to be 1.0? Thanks
-
Pretrained language models are known to prefer certain kinds of answers for spurious reasons. [Zhao 2021 ](https://arxiv.org/pdf/2102.09690.pdf) shows that GPT-3 prefers certain answer choices to mult…
-
### Problem
In https://github.com/inasafe/inasafe/blob/version-3_5_4/safe/impact_functions/earthquake/itb_earthquake_fatality_model/impact_function.py#L283 median is used on the fatalities array be…
-
In the current version of sequence generator framework it is assumed that it is always possible to emit a next token given the contexts and the previous. The `readout.emit` method is supposed to retur…
rizar updated
9 years ago
-
-
Potential readings to focus understanding on probability, mathematical statistics, algorithms, etc more deeply. Talk of applications will be secondary.
- [Statistical modeling: the two cultures](ht…
-
Hi @andrew-cr ,
Thanks for the code release,
I was wondering if you adapt the `x_0` parameterization as seen in D3PM paper ?
If so could you point me to the line in the code.
Thanks!
-
Currently (when the code works), it only returns the True/False prediction and its score (as model.Distribution objects). It may be the case that more than one, or none, of the languages are chosen as…
-
The get_results method in the lm_eval/models/openai_completions.py is not properly using the OpenAI Completion API.
Below is the API definition for LogProbs (from [openai](https://github.com/openai…
-
Environment
=============
Python 3.7.4
ImageAI 2.1.3
opencv-python 4.1.0.25
tensorflow 1.13.1
Details
========
When running the following script using a custom model, ImageAI raises an error…