-
In the file modules.py line x = x + pitch_embedding ( line no 131) the dimension of pitch_embedding is different from the dimetion of x
The same can be verified from the following logs : -
prin…
-
### 🚀 The feature, motivation and pitch
Is it possible to adapt the fine-tuning script for DPO finetuning? The current version seems to only work for next token prediction fine-tuning.
### Alternati…
-
### 🚀 The feature, motivation and pitch
I would like to propose a feature that creates a gateway for a model, allowing for multiple models to generate content within a specific context. This is simil…
-
### Title
Understand and adapt the Hybrid Predictive Coding Model
### Leaders
Louis-Clément da Costa
### Collaborators
Matthis Dallain
### Brainhack Global 2024 Event
Brainhack Marseille
### P…
-
## 🚀 Feature
## Motivation
While reading the ap calculation section of your pose branch source code, I noticed that you seem to be using bounding boxes for the ap calculation, rather than ke…
-
## 🚀 Feature
Currently, `Trainer.test` only returns logged metrics, this is very limiting.
### Motivation
I have a lot of different results which are produced by tests, including figures and sa…
-
### The Feature
Basically the same as #3247, but for Vertex AI. Blocked by #3246 as well.
https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/batch-prediction-gemini
https://cloud…
-
## 🚀 Feature
I wish you can make an example of a link prediction task using most of high level dgl features including EdgeDataLoader, heterogeneous data, dgl built in convlayers (not novel convs)?
…
-
### 🚀 The feature, motivation and pitch
PyTorch does not seem to provide wrappers to mixed precision algorithms in e.g MAGMA (dshpov, shportf) and cuSolver (https://docs.nvidia.com/cuda/cusolver/inde…
-
## Feature
Currently the MIL extension in slideflow studio redo tile extraction and feature extraction each time for slide predictions, which would take a long time. For robustness, is it possible if…