-
### System Info
As per the documentation https://github.com/huggingface/blog/blob/main/4bit-transformers-bitsandbytes.md#can-we-train-4bit8bit-models it is not possible
```
Can we train 4bit/8bit…
-
This ticket is meant as supplement to #315 as well as a place where ideas can be discussed in more detail and outside of the scheduled meeting(s). As far as I can see, we basically have these options:…
-
I'm trying to build text GAN using TF2. But gradients_of_generator always becoming [None]. Provided code below uses paddings in between generated_prediction and discriminator input. BUT even if I dir…
-
I am trying to save a simple LSTM model for text classification. The input of the model is padded vectorized sentences.
```
model = Sequential()
model.add(LSTM(40, input_shape=(16, 32)))
model.add…
-
Following #28 , I'm considering adding `inplace` argument for other functions. But I find that `inplace` operation does bring some inconsistency between the interface of vector bindings and python lis…
-
**Submitting author:** @markblokpoel (Mark Blokpoel)
**Repository:** https://github.com/markblokpoel/mathlib
**Branch with paper.md** (empty if default branch): joss
**Version:** v0.9.1
**Editor:** @d…
-
Hi, I've been on a mission to benchmark different encoders and their settings using VMAF as well as some other metrics. I get 2 main points of feedback. 1, which I think is incorrect, is that you can'…
-
I'm trying to replace dynisnt9.3 with dyninst13.0 in selectivetaint (running in ubuntu14.04 environment) and I'm getting the following error in the build from source short step, so that means that dyn…
-
The Programming Historian has received the following tutorial on 'Facial Recognition in Historical Photographs with Artificial Intelligence in Python' by @c-goldberg. This lesson is now under review a…
-
The Programming Historian has received the following tutorial on 'Finding places in text with the World Historical Gazeteer' by @apjanco and @grunewas. This lesson is now under review and can be read …