-
### Description
Creating a large compound model will result in using huge amounts of memory and/or reach the maximum recursion depth. The amount of memory used by very small models is very large.
…
-
### 🐛 Describe the bug
In deepspeed workloads, Zero parameter offload is implemented via module hooks. We find under torch.compile scenrio, if there any graph breaks happen in the pre/post hook of a …
-
Oftentimes, one wants to build linear models having ordinal variables as features (e.g. "rate in a scale from 1 to 5 ..."). One might treat these as numerical or categorical, but this loses some infor…
-
Is this out of scope? I hope not, would be nice to have a one-stop shop for interpretability tooling.
### Proposal
It should be easy to get the most bare-bones interpretability research off the…
-
I just did a "fresh install" of GoLearn for a project I am working on and noticed that it breaks under Go 1.6 with the following errors:
- .../src/github.com/sjwhitworth/golearn/ensemble/multisvc_test…
njern updated
8 years ago
-
I write a simple attention model:
```python
from torch import nn
from einops import rearrange
class Attention(nn.Module):
def __init__(self, dim = 32, heads = 3, dim_head = 8):
sup…
-
https://homes.cs.washington.edu/~marcotcr/aaai18.pdf
----
### Abstract
We introduce a novel model-agnostic system that explains the
behavior of complex models with high-precision rules calle…
-
I'm trying to use the treatment models in DML to get a prediction of the treatment. I can access the models easily with `est.models_t`
However, it's not trivial to go from those models to a predict…
-
Hi! I have been reading through the paper and [HBR_Tutorial.ipynb](https://github.com/predictive-clinical-neuroscience/PCNtoolkit-demo/blob/main/tutorials/HBR_SHASH/HBR_Tutorial.ipynb). The model work…
-
see Stata 'r.pdf' manual
estimate y with `exog_test = (fittedvalues, fittedvalues**2)`
reject correct specification if fittedvalues**2 is significant
there might be something similar for OLS already…