-
I have trained camera+lidar based on SwinT, I have got a pth. How can I generate PTQ model or FP16 model?
I used the command "python qat/ptq.py --config=configs/nuscenes/det/transfusion/secfpn/came…
-
Hi @william-silversmith ,
I have a situation where my igneous execution is stuck at one point and does not seem to progress. And I don't see any notable logs or outputs. Would you be able to guid…
-
Hi, I was investigating why HubSpot pageviews are not getting received by my HubSpot. When I install the HubSpot tracking script directly on the front-end, pageviews events are sent to `https://track.…
-
![image](https://user-images.githubusercontent.com/113669836/192921230-fd947de8-9625-41e8-a871-db3260a50f34.png)
![image](https://user-images.githubusercontent.com/113669836/192921301-c514b209-3361-4…
-
Thanks so much Robert for this great script, on a local install on a headless setup on a raspberry pi it works perfectly, however only when I launch the script from a VNC environment.
I am having d…
-
I am using a pretrained model from timm for convnextv2. It comprises of layer norm and globalresponsenormalization layer but even after adding custom quant modules for layer norm , layer norm 2d and g…
-
### Feature request
标题:
描述:
在使用 paddlenlp 进行训练和微调时,我发现 pretrain 和 sft 部分的代码实现存在一些问题,尤其是在数据集加载逻辑方面。当前实现包含了大量复杂的代码来处理数据集路径的检测和加载,这不仅影响了代码的可读性,也使得用户难以理解和维护。
当前实现问题:
```python
if data_arg…
-
General approach:
- FP training as a reference baseline / target
- PTQ as a baseline for quantization
- QAT results
- (optional) QAT starting from the FP checkpoint (i.e., finetuning)
- ana…
-
onnx_ptq/evaluate_vit.py error: ValueError: Runtime TRT is not supported.
![企业微信截图_17225064037714](https://github.com/user-attachments/assets/b1ad1ffc-9744-46ac-8d2e-ed6aeb5584a2)
-
TS INT8 degradation later versions
Hi all, I get a degradation in results after an INT8 quantization with torchscript, after updating my torch_tensorrt, torch and tensorrt versions. I have listed t…