-
# Interesting papers
- [Davison 2018 - FutureMapping: The Computational Structure of Spatial AI Systems](https://arxiv.org/abs/1803.11288)
- Imperial College London의 Dyson Robotics Lab 교수님이신 A…
-
### Describe the issue
import:
```
import sagemaker
from sagemaker.huggingface.model import HuggingFaceModel
```
code:
```
sagemaker_session = sagemaker.Session()
role = sagemaker.get_execut…
-
### Describe the issue
Issue/Error:
Loading 1.5 models works fine, but loading 1.6 models yield the error below. Note that the 1.6 models do load (despite the error) and inference works. However, tr…
-
Dear @kevin-ssy
How we can utilize TransMix for CIFAR-10 dataset? I have to conduct some experiments on CIFAR-10 dataset
-
There's small nuances in how the dynamo runners benchmark models that can make certain torchbench models fail
Some models might be explicitly skipped, others might fail because of some dtype conve…
-
Hello, I have trained a model for 40 epochs. I tried to use the `--run_from_checkpoint ./40` on another run to train the model for another 40 epochs but I'm receiving the following error:
```
`tex…
-
### System Info
If you use a model like google/siglip-so400m-patch14-384 with default settings, it will give an error that input tensors and weight dtypes are not the same.
This is because the mod…
-
Hello,
I am trying to load the model using the demo but I get
```
tokenizer, model, image_processor, context_len = load_pretrained_model(model_path, None, model_name, load_8bit=False, load_4b…
-
Although it may be out of scope, it would be nice to have an example of computing 4bit and 8bit tensors, to save memory bandwidth.
-
There are a few scenarios regarding outfit (can be co-occurring):
1. One character having multiple outfits that are routinely worn, throwing away one-off outfits
2. Multiple character wearing the sa…