-
Hi :)
Thank you for this nice crate!
I am working with multiple objectives and (if I am correct) the model misses a method to set multiple objectives including weight/priority/..-parameters simi…
-
Hi friends!
I'd like to share our recent project embodied-agents: https://github.com/mbodiai/embodied-agents, which makes it easy to integrate large multi-modal models into existing robot stacks wi…
nqyy updated
2 months ago
-
### System Info
- GPU 4 x A10G (EC2 g5.12xlarge) - memory 24GB
- TRTLLM v0.12.0
- torch 2.4.0
- cuda 12.5.1
- tensorrt 10.1
- triton 24.04
- modelopt 0.15
### Who can help?
_No response_
### Info…
-
I want to use pix2pix for a medical image generation task, where the control condition is different label images. My hyperparameter settings are as follows:
accelerate launch src/train_pix2pix_turbo.…
-
Hi is there a way to support "sentencetransformers/multi-qa-MiniLM-L6-cos-v1". It is similar to sentencetransformers/AllMiniLML6V2.
Hopefully nothing changes to produce this version, just it was t…
-
[Cosmo (cosmopolitan)](https://github.com/jart/cosmopolitan/) is a Toolchain (and Libc) for producing universal fat binaries running on any supported platform.
Some porting efforts are needed to su…
ivmai updated
3 weeks ago
-
We want to train the model on 2 gpus, so we changed the gpu="0, 1" in parameter.py. However, it still use one gpus(gpu0), and we have tried different ways but they do not work. Could you provide any s…
-
I have just realized that multi-output TFLite models do result in wrong output values using the `utvm_staticrt_codegen`. I have not look deeper into just but wanted to document this issue here. Will c…
-
If the model type name doesn't resolve as a single level then it makes a mess of creating the table name:
```perl6
use Red;
module Bar {
model Foo {
has Int $.id is serial…
-
Hi,
When I run your code on multi-gpu, performance degrades severely (compared to the single-gpu version). To make the code multi-gpu competable, I've only added 2 lines of code:
* `model = nn…