-
Hi! in the recipe, if i do not want to quantize and perform structured pruning, is it okk to give quantize:false like below and do not provide QuantizationModifier in the recipe?
SparseGPTModif…
-
Building upon the deliverables outlined in [issue #19](https://github.com/ibis-project/ibisml/issues/19), the objective is to enhance the coverage of ibisml machine learning preprocessing transformati…
-
I've tried running the demo notebook but it doesn't run majorly because it's missing arcface models.
I downloaded the model from
```
wget -P ./arcface_model https://github.com/neuralchen/SimSwap…
-
Hi, I tried running the normal train_gpt2.py code with Adam_mini. I had to remove the ValueError and Hessian spectrum import to make it work properly. I noticed that there was a good reduction in the …
-
Hello, I have to train a ST model on a very specific task, unfortunately my dataset is not big enough, therefore I was thinking to augment my data using an LLM. As my task is quite specific and demand…
-
### Have you searched existing issues? 🔎
- [X] I have searched and found no existing issues
### Desribe the bug
When I save a model with pytorch serialization, then use the model to transform the …
-
It seems that changing `k.weight` in RunAzimuth does not influence the results and does not allow to workaround the error in FindWeights function:
`> so1
-
**Describe the bug**
While using the ndarray backend, if the input to LayerNorm is a zero vector, it results in NaN during backward propagation.
**To Reproduce**
The reproduction code is as follo…
-
A short discussion among @drastogi4, Moet and @minxu74 on Oct. 14, 2020, we discussed that:
- the heat map generated by Moet contains more than 75 indices describing both mean and extreme performan…
-
I recently noticed that the wrong Android versions are being registered for Chrome users. As far as I understand, this is the problem https://developers.google.com/privacy-sandbox/blog/user-agent-redu…