运行stage2_financial_qa.sh时出现sentence-transformers和transformers版本不兼容的问题：
base_model_path: /home/lc/projects/pretrained_models/chatglm2-6b
lora_ckpt_path: /home/hf/AlphaFin-main/model/StockGPT-Stage2
embedding_model_path: /home/hf/AlphaFin-main/model/bge-large-zh
Traceback (most recent call last):
File "/home/hf/anaconda3/envs/alfin/lib/python3.9/site-packages/langchain/embeddings/huggingface.py", line 58, in init
import sentence_transformers
File "/home/hf/anaconda3/envs/alfin/lib/python3.9/site-packages/sentence_transformers/init.py", line 3, in
from .datasets import SentencesDataset, ParallelSentencesDataset
File "/home/hf/anaconda3/envs/alfin/lib/python3.9/site-packages/sentence_transformers/datasets/init.py", line 1, in
from .DenoisingAutoEncoderDataset import DenoisingAutoEncoderDataset
File "/home/hf/anaconda3/envs/alfin/lib/python3.9/site-packages/sentence_transformers/datasets/DenoisingAutoEncoderDataset.py", line 5, in
from transformers.utils.import_utils import is_nltk_available, NLTK_IMPORT_ERROR
ImportError: cannot import name 'is_nltk_available' from 'transformers.utils.import_utils' (/home/hf/anaconda3/envs/alfin/lib/python3.9/site-packages/transformers/utils/import_utils.py)
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/home/hf/AlphaFin-main/src/stage2_financial_qa/webui/run.py", line 216, in
Fire(main)
File "/home/hf/anaconda3/envs/alfin/lib/python3.9/site-packages/fire/core.py", line 135, in Fire
component_trace = _Fire(component, args, parsed_flag_args, context, name)
File "/home/hf/anaconda3/envs/alfin/lib/python3.9/site-packages/fire/core.py", line 468, in _Fire
component, remaining_args = _CallAndUpdateTrace(
File "/home/hf/anaconda3/envs/alfin/lib/python3.9/site-packages/fire/core.py", line 684, in _CallAndUpdateTrace
component = fn(*varargs, **kwargs)
File "/home/hf/AlphaFin-main/src/stage2_financial_qa/webui/run.py", line 170, in main
model, tokenizer, runner = getModel(base_model_path,
File "/home/hf/AlphaFin-main/src/stage2_financial_qa/webui/run.py", line 128, in getModel
runner = MyProcessor(embedding_model_path,
File "/home/hf/AlphaFin-main/src/stage2_financial_qa/webui/run.py", line 49, in init
self.embed = HuggingFaceEmbeddings(model_name=embedding_model_path, model_kwargs={'device': 'cpu'})
File "/home/hf/anaconda3/envs/alfin/lib/python3.9/site-packages/langchain/embeddings/huggingface.py", line 61, in init
raise ImportError(
ImportError: Could not import sentence_transformers python package. Please install it with pip install sentence-transformers.
运行stage2_financial_qa.sh时出现sentence-transformers和transformers版本不兼容的问题：
base_model_path: /home/lc/projects/pretrained_models/chatglm2-6b
lora_ckpt_path: /home/hf/AlphaFin-main/model/StockGPT-Stage2
embedding_model_path: /home/hf/AlphaFin-main/model/bge-large-zh
Traceback (most recent call last):
File "/home/hf/anaconda3/envs/alfin/lib/python3.9/site-packages/langchain/embeddings/huggingface.py", line 58, in init
import sentence_transformers
File "/home/hf/anaconda3/envs/alfin/lib/python3.9/site-packages/sentence_transformers/init.py", line 3, in
from .datasets import SentencesDataset, ParallelSentencesDataset
File "/home/hf/anaconda3/envs/alfin/lib/python3.9/site-packages/sentence_transformers/datasets/init.py", line 1, in
from .DenoisingAutoEncoderDataset import DenoisingAutoEncoderDataset
File "/home/hf/anaconda3/envs/alfin/lib/python3.9/site-packages/sentence_transformers/datasets/DenoisingAutoEncoderDataset.py", line 5, in
from transformers.utils.import_utils import is_nltk_available, NLTK_IMPORT_ERROR
ImportError: cannot import name 'is_nltk_available' from 'transformers.utils.import_utils' (/home/hf/anaconda3/envs/alfin/lib/python3.9/site-packages/transformers/utils/import_utils.py)
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/home/hf/AlphaFin-main/src/stage2_financial_qa/webui/run.py", line 216, in
Fire(main)
File "/home/hf/anaconda3/envs/alfin/lib/python3.9/site-packages/fire/core.py", line 135, in Fire
component_trace = _Fire(component, args, parsed_flag_args, context, name)
File "/home/hf/anaconda3/envs/alfin/lib/python3.9/site-packages/fire/core.py", line 468, in _Fire
component, remaining_args = _CallAndUpdateTrace(
File "/home/hf/anaconda3/envs/alfin/lib/python3.9/site-packages/fire/core.py", line 684, in _CallAndUpdateTrace
component = fn(*varargs, **kwargs)
File "/home/hf/AlphaFin-main/src/stage2_financial_qa/webui/run.py", line 170, in main
model, tokenizer, runner = getModel(base_model_path,
File "/home/hf/AlphaFin-main/src/stage2_financial_qa/webui/run.py", line 128, in getModel
runner = MyProcessor(embedding_model_path,
File "/home/hf/AlphaFin-main/src/stage2_financial_qa/webui/run.py", line 49, in init
self.embed = HuggingFaceEmbeddings(model_name=embedding_model_path, model_kwargs={'device': 'cpu'})
File "/home/hf/anaconda3/envs/alfin/lib/python3.9/site-packages/langchain/embeddings/huggingface.py", line 61, in init
raise ImportError(
ImportError: Could not import sentence_transformers python package. Please install it with
pip install sentence-transformers.