update merge weights , suit for DB-GPT

README.md

@@ -214,7 +214,7 @@ The value of the parameter  `--predicted_out_filename` is the file name of the m
 
 ### 3.5 Model Weights
 You can find the second corresponding model weights  from Huggingface [hg-eosphoros-ai
-](https://huggingface.co/Wangzaistone123/CodeLlama-13b-sql-lora)  ,we uploaded the LoRA weights in October,which execution accuracy on the Spider evaluation set reached 0.789.  
+](https://huggingface.co/Wangzaistone123/CodeLlama-13b-sql-lora)  ,we uploaded the LoRA weights in October,which execution accuracy on the Spider evaluation set reached 0.789.    
 
 #### 3.5.1 Model and fine-tuned weight merging 
 
@@ -225,7 +225,7 @@ sh ./dbgpt_hub/scripts/export_merge.sh
 ```
 
 Be sure to replace the parameter path values in the script with the paths corresponding to your project.  
-
+                                                    
 ### 3.6 Model Evaluation
 To evaluate model performance on the dataset, default is spider dev dataset.
 Run the following command:

README.zh.md

@@ -208,7 +208,7 @@ sh ./dbgpt_hub/scripts/predict_sft.sh
 ```bash
 sh ./dbgpt_hub/scripts/export_merge.sh
 ```
-注意将脚本中的相关参数路径值替换为你项目所对应的路径。   
+注意将脚本中的相关参数路径值替换为你项目所对应的路径。      
 
 
 ### 3.6、模型评估

dbgpt_hub/scripts/export_merge.sh

@@ -1,8 +1,19 @@
+# llama2 series
 python dbgpt_hub/train/export_model.py \
-    --model_name_or_path Your_base_model_path_like_Baichuan2-13B-Chat \
-    --template Your_template_like_baichuan2_eval \
+    --model_name_or_path /home/LLM/CodeLlama-13b-Instruct-hf \
+    --template llama2 \
     --finetuning_type lora \
-    --checkpoint_dir Your_ckpt_path_checkpoint-100 \
-    --output_dir Your_export_model_like_output_merge_model_baichuan2-13b-qlora_merge \
+    --checkpoint_dir dbgpt_hub/output/adapter/CodeLlama-13b-sql-lora \
+    --output_dir dbgpt_hub/output/codellama-13b-sql-sft \
     --fp16
-    # --bf16
+
+
+## Baichuan2
+# python dbgpt_hub/train/export_model.py \
+#     --model_name_or_path Your_base_model_path_like_Baichuan2-13B-Chat \
+#     --template Your_template_like_baichuan2_eval \
+#     --finetuning_type lora \
+#     --checkpoint_dir Your_ckpt_path_checkpoint-100 \
+#     --output_dir Your_export_model_like_output_merge_model_baichuan2-13b-qlora_merge \
+#     --fp16
+#     # --bf16