-
# LoRA: Low-Rank Adaptation of Large Language Models
基于large pre-trained model，把基于某个任务的微调存储在低秩矩阵对中，low intrinsic dimension $r=4$ 就够。
Pro:
- 并行化不影响速度、任务特化的信息相对很少。
- 该方法对超参数极其不敏感。
另外：
- 对于模型…
-
I am using TensorRT 5 and trying to add the code for Int8 Quantization. I tried adding the following lines in baseEngine.cpp but it is giving me an error.
builder->setInt8Mode(true);
IInt8Calibrat…
-
I'm quantizing the [MI-GAN](https://github.com/Picsart-AI-Research/MI-GAN/) network that I have previously converted to tflite successfully with your help (thank-you!)
I'm basing my conversion off …
-
After testing with the new architecture for some time, I am very impressed by its playing strength after such a relatively short training period. However, the new mish activation has proved to be quit…
-
## 🐛 Bug
LSTM network can not be evaluated after preparing for quantisation aware training. The same warning does not appear if evaluated before preparing.
## To Reproduce
Steps to reproduce…
-
# Open Grant Proposal: PrivyML as a ZKML solution on the Swan network, aims to facilitate the implementation and execution of the ZKML concept on the Swan network.
**Project Name:**`PrivyML`
**P…
-
### What is the motivation for this task?
Currently `401_nncf.ipynb` refers to the old `config.yaml` file. This should be updated to match the new API.
### Describe the solution you'd like
The solu…
-
The example [data_loader.py](https://github.com/NVIDIA/TensorRT/blob/main/tools/Polygraphy/examples/cli/convert/01_int8_calibration_in_tensorrt/data_loader.py) file used the fake data.
I want to know …
-
Thanks for sharing the awesome work!
I have one question about quantization function and bit inheritance.
In the paper, you choose LSQ as the quantization function which has a learnable scale parem…
zl-hw updated
4 years ago
-
Papers:
- LSQ+: https://arxiv.org/abs/2004.09576
- Rotated binary network: https://arxiv.org/abs/2009.13055
- PROFIT: https://link.springer.com/chapter/10.1007/978-3-030-58539-6_26
- Exponentia…