-
I am trying to use the framework to continue pretraining llama3-8B. I have converted the HF checkpoint into nanotron format and the generated tokens seem reasonable.
I use the following setting to…
-
### System information
- **Have I written custom code (as opposed to using a stock example script
provided in TensorFlow)**: yes
- **OS Platform and Distribution (e.g., Linux Ubuntu 16.04…
-
As I read it, your formula for the derivative of the sigmoid function is wrong in nn.js.
You have
```
NeuralNetwork.dSigmoid = function(x) {
return x * (1 - x);
}
```
but it should be
```
…
-
-
Hi,
I would like to apply the Laplace Subnetwork approach to a timm library model (standard resnet18). I think the problem I am encountering is not unique to timm models per se, but to inplace ope…
-
Hi, thank you for your impressing work. I have some questions about this code.
What is the role of the object 'bin_op'? It seems that it can not change the parameters 'weight' of the network 'model'?…
-
thank you for your great work!
I have trained pruned-quantized model by this command:
python3 train.py --cfg ./models_v5.0/yolov5s.yaml --recipe ../recipes/yolov5.transfer_learn_pruned_quantize…
-
I am getting memory error using the model i have trained from the tutorial, any idea? im using A10G GPU
-
### Describe the bug
Hi,
I tried to use DoReFa quantiser to train a simple model for CIFAR10, but training failed to converge:
```
10000/1 - 1s 96us/sample - loss: 2.3026 - accuracy: 0.1000
Test …
-
Hello!
First of all, thank you for this awesome project!
I'm trying to use QA to annotate fibrosis on my images and I'm not having good results. This is what my images look like
![016-22_1_4000_…