-
[The format of the issue]
Paper name/title:
Paper link:
Code link:
amusi updated
8 months ago
-
I'm attempting to replicate the results using the raw Llama 2 weights from Meta along with the example inference scripts at https://github.com/facebookresearch/llama and getting slightly different res…
-
### Description
Hello! Thanks for all of the work in this library. I was wondering if there was a straightforward way of including dropout for some of the neural networks for conditional flows. I am …
-
Would it be within the scope of the project to also support quads for meshes? That would add tremendous utility.
-
Thank you for the demo notebook. I have trained my MLM+TLM model but I get this error with training with the mt_template.json stage:
Traceback (most recent call last):
File "train.py", line 816…
-
I am trying to predict a target timeseries based on past and future covariates. However, I only have limited data for the target timeseries and in production it wont be available at all, but I have a …
-
I would like to use a separate neural network to predict LoRA weights for a main neural network, while training both neural networks at the same time. How can I manipulate the pytrees or to achieve th…
-
## Background
It’s pretty well known that neural networks, including transformers, can “memorize” data ([Intro blog post](https://bair.berkeley.edu/blog/2020/12/20/lmmem/), [Paper 1](https://arxiv.…
-
I left an issue before that was closed and after careful consideration, you were correct to do so. I apologize for coming out of the gate making claims that the repo was fraudulent. However, I am requ…
-
Following up on #94 and also our own observations about the documentation section, we need to restructure it. The idea is to split the example section into two (or more) subsections: `basic examples`…