-
May I ask for the hyperparameters used for LLaMA finetuning? The learning rate, batch size, EWC coefficient (λ), and the rank and coefficient of LoRA will be helpful.
Thank you!
-
Hello, this research is very meaningful. However, when I reproduced the performance of the default code (with default parameters) in CIFAR80N, I found that the performance of Sym-80% (33.72) and Asym-…
-
I am trying to reproduce results for SplitCIFAR-100, I used the exact same hyperparameters mentioned in the code. I am getting average accuracy as 59.42, and forgetting as 6.41.
In the paper,average …
-
> In pet it is possible to indicate not only "atomic" batch size, but also normal "structural" batch size. The same applies to SCHEDULER_STEP_SIZE, EPOCH_NUM, and EPOCHS_WARMUP. See more details in ht…
-
Dear maintainers,
I have couple questions according to hyperparameters.
1) What are the exact hyperparameters to run llama.py that are reported in Table2 for GPTVQ 2D for Llama2-7b? I am strugg…
-
### Search before asking
- [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and fou…
-
Thank you for your code. This is an outstanding job. But I cannot reproduce the results of paper FC100 based on the parameters of training two ImageNet datasets. Could you please provide me with the p…
-
Linking this to task #77 for @5u6r054 to test at scale.
Since we currently don't know if the provided implementation can support more than 1 node, we want to scale testing of the implementation.
…
-
Simply importing ConfigSpace in an environment with numpy 2.0 installed results in an error:
```
>>> import ConfigSpace
Traceback (most recent call last):
File "", line 1, in
File "/home/nol…
-
Dear Dr. Weikang Wan and Team,
I recently came across your fascinating work on the LOTUS algorithm, as detailed in your paper "LOTUS: Continual Imitation Learning for Robot Manipulation Through Un…