-
One thing I have always wanted to do is write more tutorials that empirical and theoretical economists can use to inform how they do their research. @trappmartin recently reminded me how much I have w…
-
python train.py task=HumanoidAMP experiment=AMP_walk
AttributeError: 'AMPAgent' object has no attribute 'seq_len'
``
(isaacgymenvs_hands) rob@rob-Legion-Y9000P-IRX8:~/rl/IsaacGymEnvs/isaacgyme…
-
In https://github.com/lucidrains/nGPT-pytorch/blob/main/nGPT_pytorch/nGPT.py#L350 token_embed is normalized along last dimension when it should be normalized along the first dimension.
-
### Describe the problem
I'm looking to train model with `bfloat16` datatype without having to use mixed precision on nvidia GPUs (A100 and beyond). This is important because directly using `bfloat16…
-
There are few types of transfer learning . When using TF Object Detection API do we fine tune weights of the feature extractor when using already [trained models on COCO Data Set]( https://github.com…
-
### System Info
Hello I am trying to load Mistral-Nemo Instruct-2407 in bnb 4bit on 4 A10 gpus on ec2 instance.
I upgraded all the packages.
Still I face cuda memory out of error when train batc…
-
## `gnlrem()`: that is, `gnlrim()` that allows for two random effects, possibly correlated
### the `i` changes to an `e`, but the `i` wasn't necessarily just an intercept since you had the freedom t…
-
Hi @jzluo, I found a sample dataset which fails fitting.
Consider the example data I attached here:
[sample.zip](https://github.com/jzluo/firthlogist/files/10369241/sample.zip)
```python3
#! unz…
-
It would be very useful if glmmTMB supported different types of ordinal regression, e.g. the proportional odds model (cumulative link logit model).
-
(parking a reference)
This article looks like it has a good overview of methods for meta-analysis of risk difference, based on a very brief look at the article.
Guo, Juanru, Mengli Xiao, Haitao …