-
I have modified [MobileNet model](https://github.com/camel007/caffe2-mobilenet)
```
## @package moiblenet
# Module caffe2.python.models.mobilenet
from __future__ import absolute_import
from __f…
-
# Context
Documenting field-level explicit likelihood inference from a differentiable cosmological model.
In [code](https://github.com/hsimonfroy/montecosmo/blob/a7346788b5555b2f6b14bff3e9dc2f4c9…
-
### 🐛 Describe the bug
When using FSDP (Fully Sharded Data Parallel) to save a model, some parameters are not fully gathered on rank 0 and therefore not properly saved. This issue occurs specifical…
-
Hi,
Thanks a lot for the excellent work. I'm trying your code out on a single view case where I want to enable the shadow visibility gradients. How can I do that in the code, i.e. how to reproduce …
-
I kept getting this error
# ComfyUI Error Report
## Error Details
- **Node Type:** MochiWrapperSamplerCustom
- **Exception Type:** RuntimeError
- **Exception Message:** slow_conv2d_forward_mps:…
-
### Description
The OMPL planners that use goal biasing (RRT, RRTstar, etc.) do not perform goal biasing because the Goal object passed into OMPL via Moveit's OMPL interface is not sample-able. Spe…
-
**Is your feature request related to a problem? Please describe.**
Users of TADA have noted that it would be useful to incorporate replicate field samples into water quality data analysis by flaggi…
-
### OS
Windows
### GPU Library
CUDA 12.x
### Python version
3.12
### Pytorch version
2.4.1+cu121
### Model
Qwen/Qwen2.5-72B-Instruct
### Describe the bug
Qwen 2.5 72B …
-
### 🐛 Describe the bug
I've been trying to implement T5 encoder relative attention bias in flex_attention.
I came up with a few algorithms for it, and a benchmark script:
https://gist.github.…
-
### Describe the bug
For requests to endpoints (i sended only to chat/completions), auto_max_new_tokens is somehow always True, even if it is False
```python
if state['auto_max_new_tokens']: # al…