-
Hello,
I ran tflite quantization process on several ResNet neural network. When I want to test the accuracy of the tflite model and the tflite quantized model it is display 100000.0000%
Here the…
-
最终报错：
[INFO|training_args.py:1345] 2023-11-12 17:25:17,617 >> Found safetensors installation, but --save_safetensors=False. Safetensors should be a preferred weights saving format due to security and…
-
### 软件环境
```Markdown
- paddlepaddle: \
- paddlepaddle-gpu: 2.4.2
- paddlenlp: "2.5.2.post" (直接拉的代码，再pycahrm自定义模型训练)
```
### 重复问题
- [X] I have searched the existing issues
### 错误描述
```Markdown…
-
### Issue type
Bug
### Have you reproduced the bug with TensorFlow Nightly?
No
### Source
binary
### TensorFlow version
2.13.0
### Custom code
Yes
### OS platform and distribution
mac os 12…
-
### Describe the bug
When creating a custom HuggingFace pipeline, with bentoml.transformers.save_model(...),
In my ~/bentoml/models/my_pipeline/[latest]/ directory, the model is stored both as p…
-
I create a Visual Transformer (VIT) for image classification.
After that i create the model using Tensorflow, i obtain a .pb folder with these files inside:
- 2 folders "assets" and "variables"
…
-
This looks great!
But I ran into an out of memory error while running the code. The device I'm using is RTX 3090, 24G. Could you share some information on how much memory is needed to run this code…
-
I'm trying extend my parametrized quantum circuit to use data re-uploading, as proposed by [Pérez-Salinas et al.](https://arxiv.org/pdf/1907.02085.pdf)
Currently, my model exists of a single Input…
-
Click to expand!
### Issue Type
Bug
### Source
source
### Tensorflow Version
2.9
### Custom Code
No
### OS Platform and Distribution
Ubuntu 20.04
### Mobile device
…
-
Just a heads up on CFG, a technique in which: "Models can perform as well as a model 2x as large" at the cost of 2x the computation, but that is negligible if it improves 65B to a 130B-class LLM.
T…