update setup

FlagEmbedding/BGE_M3/README.md

@@ -187,7 +187,7 @@ print(model.compute_score(sentence_pairs,
   - MLDR:
   ![avatar](./imgs/long.jpg)
   Please note that MLDR is a document retrieval dataset we constructed via LLM, 
-  covering 13 languages, including test sets, validation sets, and training sets. 
+  covering 13 languages, including test set, validation set, and training set. 
   We utilized the training set from MLDR to enhance the model's long document retrieval capabilities. 
   Therefore, comparing baseline with `Dense w.o.long`(fine-tuning without long document dataset) is more equitable. 
   Additionally, this long document retrieval dataset will be open-sourced to address the current lack of open-source multilingual long text retrieval datasets.

examples/finetune/README.md

@@ -17,6 +17,8 @@ For development, install as editable:
 ```
 pip install -e .
 ```
+
+The new version of Transformers may pose issues for fine-tuning. If you encounter problems, you can try to downgrade to versions 4.33-4.36.
 
 
 ## 2. Data format

setup.py

@@ -5,7 +5,7 @@
 
 setup(
     name='FlagEmbedding',
-    version='1.2.2',
+    version='1.2.3',
     description='FlagEmbedding',
     long_description=readme,
     long_description_content_type="text/markdown",
@@ -14,7 +14,7 @@
     packages=find_packages(),
     install_requires=[
         'torch>=1.6.0',
-        'transformers==4.33.0',
+        'transformers>=4.33.0',
         'datasets',
         'accelerate>=0.20.1',
         'sentence_transformers',