-
### Request description
Per discussion in: https://github.com/openxla/stablehlo/pull/2586#discussion_r1799945650, we should consider what sorts of flags / options the simplification and folding pas…
-
# Write a Blog Post: How to Set Up Goose on Windows 🦢
[Goose](https://github.com/block/goose) is your on-machine developer agent, automating engineering tasks seamlessly within your IDE or terminal. G…
-
Hi Jaehong I recently read your article on Tensorflow: [https://blog.tensorflow.org/2022/06/Adding-Quantization-aware-Training-and-Pruning-to-the-TensorFlow-Model-Garden.html](https://blog.tensorflow.…
-
**Short Description**
Add support for anchor box customization within the keras_cv.models.YOLOV8Detector class. This would allow users to:
- Specify custom anchor boxes during model creation
- …
-
When creating train+val loaders for tuning CNNs for vision data, the following traceback is received:
```
INFO 05-12 21:06:37] ax.service.utils.instantiation: Inferred value type of ParameterType…
-
### Describe the issue
when using yolov8 fp32 onnx model by qnn， it runs successfully in Snapdragon 8 Gen 2 (SM8550 pnone: redme k70)，but it run failedly in Snapdragon 8888 (SM8350 phone: realme gt…
-
Has anyone tried downscaling the K and/or Q matrices for repeated layers in franken-merges? This should act like changing the temperature of the softmax and effectively smooth the distribution:
**H…
-
### Issue Description
I installed it via Pinokio, and running anything above 512x512 batch 1 does OOM at my 8Gb 2070S, I never had anything like that with other SD software. Even enabling Nvidia's …
-
I reimplemented dpo in my own dataset and model, and the model tends to generate answers of increasing length:
![image](https://github.com/eric-mitchell/direct-preference-optimization/assets/46637504…
-
I was wondering if it where possible to develop an new booster, that instead of taking the mean of values inside a leaf instead fitted a linear function. In cases of lower numbers a features its possi…