-
## Description
- error: 'ttnn.conv2d' op Bias must only have data on the final dimenstion in vgg variants
## Reproduce
```
git checkout kkannan/vgg_conv2d_issue
git submodule update --recursive
# …
-
## Instructions To Reproduce the Issue:
I installed Detectron2 and attempted to train the ViTDet base model from the documentation provided here: https://github.com/facebookresearch/detectron2/tree…
-
In some exported model with ConvTranspose I'm seeing the wrong shape for bias:
. When I'm trying to launch example, i got…
-
some logs:
#source shell_scripts/export_llama.sh qwen2 "" "" "" llama3.txt
checkpoint_files: ['models/llm_models/weights/Qwen2.5-0.5B-Instruct/model.safetensors']
Preparing Model Calibration In…
-
I have trained a Recurrent network using an LSTMCell and MLP layers. But when I load the model and the weights for running the benchmark, I get "RuntimeError: output with shape [256] doesn't match the…
-
Hi! I tried to run inference.py but encoutered below error as it seems indicating some missing keys and mismatches.
I believe I have set up the checkpoints files correctly.
For the LLaMA model, I m…
-
I'm trying to evaluate metric with different models, it works fine with the default `l`, but if I change it to `s` like this:
```
@staticmethod
def build(train_midas=False, fetch_features…
-
Click to expand!
### Issue Type
Bug
### Source
binary
### Tensorflow Version
tf 2.4 - v2.4.0-rc4-71-g582c8d236cb 2.4.0
### Custom Code
No
### OS Platform and Distribution…
-
### 🐛 Describe the bug
Hi I want to use autocast with a script model and had the following error.
```python
import torch
import torch.nn as nn
from torch.amp import autocast
class SimpleC…