-
**Description**:
The RL and IRL algorithms need tuning to perform well (especially the Adversarial ones). We need to put some time and tune them and see if they can perform well if we want to use the…
Erfi updated
10 months ago
-
How to do hyper parameter tuning for SB3 algorithm such as PPO, A2C, DQN?
-
I did a benchmark to check the time cost (us) of cublas and triton on various shapes, I find that triton kernel is faster than cublas on most of the times.
Is that a normal case? Anyone got the s…
-
Here is a snapshot from `_libs/nav/head.js` which is responsible for routing data:
```julia
{
name: "Getting Started",
id: "getting-started",
href: "/info/getting-started",
sec…
-
Hi, thank you for the great library.
Recently, many algorithms are proposed to replace fine-tuning as it incurs too many burdens, especially with huge models like GPT3. Examples include [P-tuning](…
-
Define the core milestones to achieve in terms of program components and routines?
## Define software stack
Composing a software stack is the most important part of this work, since my code will only…
-
## Background information
I'm tuning OpenMPI's alltoall on our cluster.
### What version of Open MPI are you using? (e.g., v4.1.6, v5.0.1, git branch name and hash, etc.)
v5.0.3
### Describ…
-
It would be great if it could support BERT, LLaMA and other model training.
-
Hi, Thank you for sharing this amazing open source. I've tried to fine tune grounding DINO as open set because fine-tuned grounding DINO as closed set is not compatible with grounded SAM repo. I guess…
-
### Description
Mesh tuning currently takes way too long especially on large number of nodes (>= 2 nodes). We can bypass this if a prediction can be made based on a linear interpolation of mesh sizes…