-
@ItzCrazyKns I think this request is a bit different from #72. That issue is about system prompts for various tasks, but the preferred output language is a separate thing. Adding a setti…
-
Hey,
Thanks for maintaining this list. I do not want to submit multiple pull requests without asking first if I should do that (since it's work for you and also for me)
I have a few projects whi…
-
First, I find the added value of using Sigma in this solution rather small and the solution could also have been written in normal Java, even. Therefore, I think the solution is rather about MOEA than…
-
How to render the depth map from SA3D?
-
Bergamot is a consortium coordinated by the University of Edinburgh with partners Charles University in Prague, the University of Sheffield, University of Tartu, and Mozilla. [1]
Since I just teste…
okias updated
2 years ago
-
Hi,
Thanks for providing such a great tool to machine translation system.
I am currently building an online system with multi-way to access the translation system. I am using the translate_server.…
-
Hi, I have a tricky problem with m2m field and admin intergration. I want to make m2m field translatable.
Let say I have a model Product:
```
class Product(TranslatableModel):
translations = Tran…
-
For task specific domain adaption support for [LoRA](https://arxiv.org/abs/2106.09685) weights is needed for a variety of use cases for LLM and Diffusion models:
1. On mobile where base foundation…
-
I was inspecting intermediate values of the output tensor `transformer.h`, while running `marian_decoder`, and noticed that the first step through the decoder some sort of token is passed that has 0 w…
-
## 🐛 Bug
### To Reproduce
Steps to reproduce the behavior (**always include the command you ran**):
I don't have a small enough MWE...
1. Run any finetuning command on a model original…