-
### This is my env version:
```
torch:2.2.1
transformers: 4.39.0.dev0
vllm: custom compile at master@24aecf421a4ad5989697010963074904fead9a1b
```
### I use SqueezeLLM quantization my llama-7B tr…
-
It might be good to have specific shaders for gradients made of 2 colors or less - a very common use case. These shaders do not need precalculated color ramps ( -> textures ) as such an interpolation …
-
Hello,
First, congratulations on release of Mamba 2.0.
I wanted to let you know that I have published a fork of Mamba 1.0 that much like Mamba 2.0 happens to add support for multi-head SSMs, as…
-
I am referring to the gradient derivation [here](https://huggingface.co/learn/deep-rl-course/unit4/pg-theorem#optional-the-policy-gradient-theorem).
The paragraph where the instructor claimed "we c…
-
Hi, thanks so much for providing this library!
I am implementing a multi-step optimization problem where I am using two models (visual_encoder resnet and a coefficient_vector) to calculate a weigh…
-
## Describe the bug
From my experiments it seems like the sign for the Ranger is inverted. All other optimizers (including Ranger21) has steps in the opposite direction of Ranger.
Note that I'm…
-
In https://github.com/w3c/csswg-drafts/issues/2532 it was discussed to allow one-dimensional images in two-dimensional contexts. Lately [it was resolved](https://github.com/w3c/csswg-drafts/issues/253…
-
I'd tried my hand at un-typed weight decay as follows:
```
import qualified Torch.Functional as F
import qualified Torch.Tensor as D
import qualified Torch.Optim …
-
### MDN URL
https://developer.mozilla.org/en-US/docs/Web/CSS/gradient/linear-gradient
### What specific section or headline is this issue about?
[Formal syntax](https://developer.mozilla.org/…
-
Hi,
I am asking for this new feature because I got quite confused when I watch multiple networks at the same time in one run. In my case there are 4 different networks (nn.Modules) and each of the…