Soulscb
Soulscb
Now,I want to convert to tflite,but the tflite_convert is wrong. I don’t know is the Albert support convert 发自我的iPhone ------------------ Original ------------------ From: brightmart
i think the model inference is too slow and how do you speed up it
wenlan2.0的论文哪里有？
Traceback (most recent call last): File "/data/11103440/code_gen_eval_bin/awq_quantize.py", line 26, in model.quantize(tokenizer, quant_config=quant_config, calib_data=calib_data) File "/usr/local/lib/python3.10/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, **kwargs) File "/usr/local/lib/python3.10/dist-packages/awq/models/base.py", line 231, in quantize self.quantizer.quantize() File...
> +1, I have the same error with Gemma 2 27B-it (on AutoAWQ Gemma branch) do you solve it?
do you solve your problem?
have you solved it