cooper
cooper
> AWQ takes a different approach, where it leaves part of the model un-quantized, and it quants the rest to 4bit. From reading the whitepaper, there is no longer a...
我也是，但是加载案例是没有这个问题的，就是加载自己通过museV生成的视频，会导致这个问题， ``` video in 50.0 FPS, audio idx in 50FPS extracting landmarks...time consuming reading images... 100%|██████████████████████████████████████████████████████████████████████████| 251/251 [00:00
+1, waiting for
> @bao21987 Confirm, and you can access. can you give me the access to visit it? thanks
+1,qwen2.5-72b-instruct-awq量化之后
> Hi, if you quantize the 72B model on your own, please refer to [troubleshooting](https://qwen.readthedocs.io/en/latest/quantization/gptq.html#troubleshooting) of our docs to first pad the parameters before quantization. Also be aware that the...
+1, qwen2.5-72b-instruct
has solve it?
does anyone has a solvtion?