nlp遇到的问题

1.AttributeError: 'CodeGenTokenizer' object has no attribute 'encoder'

pip install transformers==4.33.2

2.ImportError: Using `low_cpu_mem_usage=True` or a `device_map` requires Accelerate: `pip install accelerate`

pip install accelerate

3.python eval_fewshot.py --data_path "data/ARC-Easy-validation.jsonl" --device_id "0" --model ./mo/phi-1_5 --embedder ./em/bge-small-en-v1.5 --start_index 0 --end_index 9999 --max_len 1024 --output_path ./output --overwrite False --prompt_type "v2.0" --N 8 --top_k Ture --top_k_reverse False

4.运行到800个json的时候报错，因为系统盘不够用了，扩容