Update README.md

README.md

@@ -148,6 +148,9 @@ HIP_VISIBLE_DEVICES=0 swift export --model_type telechat-7b \
     --quant_bits 8 --quant_method gptq --model_id_or_path /path/to/telechat-7b \
     --quant_output_dir ./quant_out
 ```
+如果GPTQ量化遇到：RuntimeError: The weights trying to be saved containhed shared tensors [{'lm_head.weight', 'transformer.word_embeddings.weight'}] that are mismatching the transformers base configuration. Try saving using 'safe serialization=False` or remove this ternsor sharing，
+可尝试找到文件/usr/local/lib/python3.10/site-packages/optimum/gptq/quantizer.py，并修改676行为safe_serialization=False
+
 
 ### 量化后推理