-
使用的原始模型是./models/pretrained/nanotrackv3.pth
转换步骤为pth转pt,利用pnnx转ncnn。
[backbone127的pt模型](https://github.com/Sherlock-hh/bug_record/blob/main/nanotrackv3_backbone127.pt)
[backbone255的pt模型](https://gi…
-
Hi, I want to quantize Mixtral model to fp8. I have a single H100 GPU. The original model doesn't fit on a single GPU (but quantized does). Up until https://github.com/NVIDIA/TensorRT-LLM/pull/1598, t…
bprus updated
4 months ago
-
### Search before asking
- [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and fou…
-
https://huggingface.co/mistral-community/Mixtral-8x22B-v0.1/tree/main
This is way more powerful than the previous Mixtral, on essentially all benchmarks
Tried quantizing this myself, it seemed …
-
My axis camera is AXIS P1467-LE Bullet Camera, and I was able to successfully upload the yolov5n tflite model to it. I want to use that yolov5n tflite model, but I am struggling with post-processing t…
-
### Please check that this issue hasn't been reported before.
- [X] I searched previous [Bug Reports](https://github.com/OpenAccess-AI-Collective/axolotl/labels/bug) didn't find any similar reports.
…
-
aqt doesn't support quantization of complex-valued operations. I fixed this temporarily by decomposing complex operations into real and imaginary parts like
```
A @ B => (A.real @ B.real - A.imag…
-
Quantizing CesiumMan with `gltf-transform quantize CesiumMan.glb CesiumMan+quant.glb` we see validation errors and visible 'spikes' in the geometry. Problem appears related to sorting and normalizing …
-
I'm trying to quantize my model to int8 and pass the dataset as int8_calib_dataset. But it looks like the calibration is ignoring the data from the dataset and instead optimizing only the single batch…
-
I just installed Rawtherapee on a Windows 10 laptop, which comes with a decent trackpad and a handful of useful gestures. I'm most interested in the zoom and swipe to scroll between photos.
Looking…