-
Hi there,
thanks a lot for all your great repos and implementations!
I've wanted to try this for a segmentation problem and I've had issues training on colabs 40GB GPU with dimensions 256x256. …
-
I believe that our current functions for computing the max-min ordering and nearest neighbors could be improved to reduce running time. Specifically, I believe our current implementations are O(n^2) b…
-
With regards to the latest current commit (https://github.com/kunwu522/certified_edge_unlearning/tree/1afbbff249feb10b55246fed51fa21cedab5232d):
I see that experiment.py is importing the train_mia …
-
Given that MegaBlocks is highly optimized for sparse MoE models like Mixtral, I am requesting support for a variant recently termed as MoDE by Google DeepMind. Benefits include much faster training an…
-
We propose [MeteoRA: Multiple-tasks Embedded LoRA for Large Language Models](https://arxiv.org/pdf/2405.13053). Our proposed MeteoRA (Multiple-Tasks embedded LoRA) is a scalable and efficient framewor…
-
Hello! Thanks for open-sourcing the realization of code for this paper!
I can't understand what file contains the correct implementations: `models/copynet.py ` or `models/copynet_dbg.py`: the former …
-
In the published paper on FunSearch, there is a mention of using pre-trained large language models (LLMs) like Codey (based on the PaLM2 model family) and a reference to StarCoder, an open-source LLM,…
-
Hi Lu,
I'm currently trying to reproduce your paper results on CIFAR100 and I was wondering which triplet loss version you used since you provided two implementations in your repository ([triplet.py]…
-
The author of the article "Paxos made simple" says in his website that this article contains an ambiguous sentence that may lead to incorrect implementations:
http://lamport.azurewebsites.net/pubs/pu…
-
You said that you tried integrating DKM in your sfm framework and obtained better results than LoFTR in last year's Image Matching Challenge -- would you release the code for that?