在 Qwen-14B-Chat-Int4推理时,发现报错,缺少 optimum 和 auto-gptq 两个pip包
Traceback (most recent call last):
File "test_qwen_14b_int4.py", line 6, in <module>
model = AutoModelForCausalLM.from_pretrained(
File "/home/linewell/anaconda3/envs/codeS/lib/python3.8/site-packages/transformers/models/auto/auto_factory.py", line 558, in from_pretrained
return model_class.from_pretrained(
File "/home/linewell/anaconda3/envs/codeS/lib/python3.8/site-packages/transformers/modeling_utils.py", line 2584, in from_pretrained
raise ImportError(
ImportError: Loading GPTQ quantized model requires optimum library : `pip install optimum` and auto-gptq library 'pip install auto-gpt