-
# Captum LIME API Design
## Background
LIME is an algorithm which interprets a black-box model by training an interpretable model, such as a linear model, based on local perturbations around a p…
-
I wonder if PyTorch hybrid sparse/dense tensors can be used to represent outputs of dimension-wise topk / min / max. Unfortunately I couldn't completely understand from docs if they can be used for th…
-
**Describe the bug**
I have setup pg_vector like so:
```
from vanna.pgvector import PG_VectorStore
from vanna.openai import OpenAI_Chat
class CustomVanna(PG_VectorStore, OpenAI_Chat):
de…
-
## Issue
Currently we assume few things in jetstream which hinders it's generalization:
1. tokenizer is SentencePiece based.
2. pad_id is 0
3. after encode, we pad to nearest power of 2
4. Re…
qihqi updated
5 months ago
-
This is a subset distribution that includes all of **sagemath-standard** except for `sage.symbolic` and modules that use that.
As preparation, we remove gratuitous module-level imports from `sa…
-
Project Name: ImpQAlgo4Qchem
Team Name: Tensor Algebra
Which challenges would you like to submit your project for?
Quantum Chemistry Challenge
Quantum computing today!
NVIDIA Challenge
Pow…
-
While looking into the WebGPU backend and execution example I am left with a few questions.
I am currently working on porting the[ Open Image Denoise](https://github.com/RenderKit/oidn) models to w…
-
## 🚀 Feature
Support graph pooling operation on cliques.
## Motivation
Graph coarsening is common in tasks where we try to extract graph features from different scales. Usually, the input graph…
-
This tracking is meant to list the main improvements we'll be focusing on for sparse tensors, and then mapping them to the releases they should land in. _Please note: these are estimates and indicate …
-
The following code for the contiguous check in **shape.rs** will trigger problems for the squeezed tensor (n-dim to 1-dim) because of the " if dim > 1" condition (recently added ).
``` rust
//…