-
First of all, thanks for developing this excellent library!
My strategy will enter short/long position right after closing long/short position, while short/long signal happens. And each postion wil…
-
问题1:
我使用PaddleSeg-release-2.8.1 的方式进行训练自己的数据集,然进行感知量化训练 在PaddleSeg-release-2.8.1/deploy/slim/quant文件下进行了训练 动态转静态 。然后使用 paddle2onnx的静态文件转onnx文件 没有生成 onnx为文件
(PaddleSeg) D:\PY\PaddleSeg-rele…
-
I used auto_gptq 0.7.1 and run this code:
python quant_with_alpaca.py --pretrained_model_dir Qwen1.5-14B-Chat --quantized_model_dir Qwen1.5-14B-Chat_4bit --use_triton --save_and_reload --trust_remote…
-
按照paddleslim/example/auto_compression的Readme.md进行操作,运行运行自动化压缩时报错:
```
Traceback (most recent call last):
File "/aidata/CYHan/auto_compass.py", line 42, in
ac.compress()
File "/root/ana…
-
**Describe the bug**
```
2023-05-31 11:33:20 INFO [auto_gptq.modeling._base] Quantizing mlp.dense_4h_to_h in layer 7/70...
Traceback (most recent call last):
File "quant_with_alpaca.py", line 17…
-
hi, How do i improve the inference time of my Llama2 7B model?....
i used BitsAndBytesConfig also but this does not seem to fasten the inference time!
code:
`name = "meta-llama/Llama-2-7b-cha…
-
v 0.6.1
```bash
python quantize.py --model_dir ./hg_weight_3999/ --dtype float16 --qformat int4_awq --export_path ./quantized_int4-awq --calib_size 32
```
```log
Using pad_token, but it is not se…
-
Hi, can you share best practices for quantization for CNN models?
Are the modelopt quantized PTQ is the way to go with tensorrt for cnn models (resnet retinanet etc)? I was able to quantize retinanet…
-
I ran mem_spd_test.py and got the following error:
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cuda:1!
I did not make any changes except …
-
In [README.md](https://github.com/olxgroup-oss/libvips-rust-bindings/blob/v1.7.0/README.md), libvips is noted as 8.14.5, however, the test example in which executed failed with the following error.
…