-
There does not appear to be any clear definition of what parameters a success criteria must meet in order to qualify for any particular conformance level.
In order to be considered Conformance Leve…
-
Hi. I'm trying to make my own environment using this package for my own robot with its own task. Things to consider:
- I'm using TQC algorithm.
- I'm defining my own task, which uses the position …
-
**Describe the bug**
Using ludwig serve from the cmd , Model reserves gpu memory but does not utilize gpu at all. Although unlike https://github.com/ludwig-ai/ludwig/issues/73 , training works well o…
-
**What version of Tailwind CSS are you using?**
V3.1.5
**What build tool (or framework if it abstracts the build tool) are you using?**
Next.js 12.2.0
**What version of Node.js are you using?*…
-
When I use this project to finetune the Mixtral8*7B model, there is an FileNotFoundError found.
The error message is :
File "/home/pai/envs/llama_etuning/lib/python3.9/site-packages/transform…
-
Hello, I managed to run SHALLOW and DELTA, but when I run DEEP with
```
python -u train.py \
--dataset ${dataset} \
--annotation ${annotation} \
--base_dir ${base_dir} \
--batc…
-
Is there a versatile transformers-like API (like model.generate()) equivalent for this? I tried JAXServer but it is quite confusing, and I couldnt get flashattention to work. Could you maybe provide s…
-
### Describe the feature request
Currently the proposer and the prover are completely separated. In practice however it's extremely likely block builders already know provers. It's also possible to…
-
Hi there.
I have seen a bit of confusion in the community around the beam search procedure and the returned classes, particularly the `scores` attribute. This seemed to be the motivation behind th…
-
Hi!
i was running few experiments and noticed that GP is extremely hight in first few 100 steps.
GP > 60000, and then gradually going down to around GP = 20
is it normal behaviour? In my previo…