change figures' path

README.md

@@ -1,7 +1,4 @@
-<<<<<<< HEAD
-=======
 ---
->>>>>>> 2e37a45df21ce9449428b7afc0e170a6dd7042b0
 license: mit
 language:
 - en
@@ -13,7 +10,7 @@ base_model:
 - deepseek-ai/deepseek-coder-7b-instruct-v1.5
 library_name: transformers, alignment-handbook
 pipeline_tag: question-answering
-<<<<<<< HEAD
+---
 
 ### 1. Introduction of this repository
 
@@ -27,20 +24,20 @@ Official Repository of "Can Large Language Models Analyze Graphs like Profession
 
 #### The pipeline of ProGraph benchmark construction
 
-<img width="1000px" alt="" src="https://huggingface.co/spaces/lixin4sky/ProGraph/blob/main/figure_1_the_pipeline_of_ProGraph_benchmark_construction.jpg">
+<img width="1000px" alt="" src="figures/figure_1_the_pipeline_of_ProGraph_benchmark_construction.jpg">
 
 #### The pipeline of LLM4Graph dataset construction and corresponding model enhancement.
 Code datasets. We construct two code datasets in the form of QA pairs. The questions in both datasets are the same, but the answers differ. In the simpler dataset, each answer only contains Python code. Inspired by Chain of Thought (CoT) [55], each answer in the more complex dataset additionally includes relevant APIs and their documents as prefixes. This modification can facilitate open-source models to utilize document information more effectively. We name the above code datasets as Code (QA) and Doc+Code (QA), respectively. Unlike the hand-crafted benchmark, problems in the code datasets are automatically generated and each contains only one key API.
 
-<img width="1000px" alt="" src="https://huggingface.co/spaces/lixin4sky/ProGraph/blob/main/figure_2_the_pipeline_of_LLM4Graph_dataset_construction_and_corresponding_model_enhancement.jpg">
+<img width="1000px" alt="" src="figures/figure_2_the_pipeline_of_LLM4Graph_dataset_construction_and_corresponding_model_enhancement.jpg">
 
 #### The pass rate (left) and accuracy (right) of open-source models with instruction tuning.
 
-<img width="1000px" alt="" src="https://huggingface.co/spaces/lixin4sky/ProGraph/blob/main/figure_4_the_pass%20rate_and_accuracy_of_open-source_models_withe_instruction_tuning.jpg">
+<img width="1000px" alt="" src="figures/figure_4_the_pass rate_and_accuracy_of_open-source_models_withe_instruction_tuning.jpg">
 
 #### Compilation error statistics for open source models.
 
-<img width="1000px" alt="" src="https://huggingface.co/spaces/lixin4sky/ProGraph/blob/main/figure_6_compilation_error_statistics_for_open-source_models.jpg">
+<img width="1000px" alt="" src="figures/figure_6_compilation_error_statistics_for_open-source_models.jpg">
 
 #### Performance (%) of open-source models regarding different question types.