Improve model card: Add metadata, update introduction, and add citation

README.md

@@ -3,25 +3,30 @@ license: mit
 tags:
 - decompile
 - binary
+datasets:
+- LLM4Binary/decompile-bench
+pipeline_tag: text-generation
+library_name: transformers
 ---
 
-### 1. Introduction of LLM4Decompile
+# LLM4Decompile-6.7B-v2 Model Card
 
-LLM4Decompile aims to decompile x86 assembly instructions into C. The newly released V2 series are trained with a larger dataset (2B tokens) and a maximum token length of 4,096, with remarkable performance (up to 100% improvement) compared to the previous model.
+This repository contains **LLM4Decompile-6.7B-v2**, an open-source large language model dedicated to decompilation, presented in the paper [Decompile-Bench: Million-Scale Binary-Source Function Pairs for Real-World Binary Decompilation](https://huggingface.co/papers/2505.12668).
 
-- **Github Repository:** [LLM4Decompile](https://github.com/albertan017/LLM4Decompile)
+The LLM4Decompile project aims to decompile x86 assembly instructions into human-readable C source code. This specific `v2` model is part of the **LLM4Decompile-Ref** series, building upon **Ghidra** to **refine** the decompiled pseudo-code. It is trained on 2 billion tokens with a maximum token length of 4,096, demonstrating remarkable performance (up to 100% improvement) compared to previous models.
 
+-   **GitHub Repository:** [LLM4Decompile](https://github.com/albertan017/LLM4Decompile)
 
 ### 2. Evaluation Results
 
 |         Metrics         | Re-executability Rate |         |         |         |         | Edit Similarity |         |         |         |         |
-|:-----------------------:|:---------------------:|:-------:|:-------:|:-------:|:-------:|:---------------:|:-------:|:-------:|:-------:|:-------:|
-|    Optimization Level   |           O0          |    O1   |    O2   |    O3   |   AVG   |        O0       |    O1   |    O2   |    O3   |   AVG   |
-|  LLM4Decompile-End-6.7B |        0.6805         | 0.3951  | 0.3671  | 0.3720  | 0.4537  |     0.1557      | 0.1292  | 0.1293  | 0.1269  | 0.1353  |
-|          Ghidra         |        0.3476         | 0.1646  | 0.1524  | 0.1402  | 0.2012  |     0.0699      | 0.0613  | 0.0619  | 0.0547  | 0.0620  |
-|         +GPT-4o         |        0.4695         | 0.3415  | 0.2866  | 0.3110  | 0.3522  |     0.0660      | 0.0563  | 0.0567  | 0.0499  | 0.0572  |
-| +LLM4Decompile-Ref-1.3B |        0.6890         | 0.3720  | 0.4085  | 0.3720  | 0.4604  |     0.1517      | 0.1325  | 0.1292  | 0.1267  | 0.1350  |
-| +LLM4Decompile-Ref-6.7B |        0.7439         | 0.4695  | 0.4756  | 0.4207  | 0.5274  |     0.1559      | 0.1353  | 0.1342  | 0.1273  | 0.1382  |
+|:-----------------------:|:---------------------:|:-------:|:-------:|:-------:|:-------:|:---------------:|:-------:|:-------:|:-------:|:-------:|\
+|    Optimization Level   |           O0          |    O1   |    O2   |    O3   |   AVG   |        O0       |    O1   |    O2   |    O3   |   AVG   |\
+|  LLM4Decompile-End-6.7B |        0.6805         | 0.3951  | 0.3671  | 0.3720  | 0.4537  |     0.1557      | 0.1292  | 0.1293  | 0.1269  | 0.1353  |\
+|          Ghidra         |        0.3476         | 0.1646  | 0.1524  | 0.1402  | 0.2012  |     0.0699      | 0.0613  | 0.0619  | 0.0547  | 0.0620  |\
+|         +GPT-4o         |        0.4695         | 0.3415  | 0.2866  | 0.3110  | 0.3522  |     0.0660      | 0.0563  | 0.0567  | 0.0499  | 0.0572  |\
+| +LLM4Decompile-Ref-1.3B |        0.6890         | 0.3720  | 0.4085  | 0.3720  | 0.4604  |     0.1517      | 0.1325  | 0.1292  | 0.1267  | 0.1350  |\
+| +LLM4Decompile-Ref-6.7B |        0.7439         | 0.4695  | 0.4756  | 0.4207  | 0.5274  |     0.1559      | 0.1353  | 0.1342  | 0.1273  | 0.1382  |\
 |  +LLM4Decompile-Ref-33B |        0.7073         | 0.4756  | 0.4390  | 0.4146  | 0.5091  |     0.1540      | 0.1379  | 0.1363  | 0.1307  | 0.1397  |
 
 ### 3. How to Use
@@ -71,28 +76,29 @@ with tempfile.TemporaryDirectory() as temp_dir:
         executable_path = os.path.join(temp_dir, f"{pid}_{opt}.o")
         cmd = f'gcc -{opt} -o {executable_path} {func_path} -lm'
         subprocess.run(
-        cmd.split(' '),
-        check=True,
-        stdout=subprocess.DEVNULL,  # Suppress stdout
-        stderr=subprocess.DEVNULL,  # Suppress stderr
-        timeout=timeout_duration,
+        cmd.split(' '),\
+        check=True,\
+        stdout=subprocess.DEVNULL,  # Suppress stdout\
+        stderr=subprocess.DEVNULL,  # Suppress stderr\
+        timeout=timeout_duration,\
         )
 
         output_path = os.path.join(temp_dir, f"{pid}_{opt}.c")
-        command = [
-            ghidra_path,
-            temp_dir,
-            project_name,
-            "-import", executable_path,
-            "-postScript", postscript, output_path,
-            "-deleteProject",  # WARNING: This will delete the project after analysis
-        ]
+        command = [\
+            ghidra_path,\
+            temp_dir,\
+            project_name,\
+            "-import", executable_path,\
+            "-postScript", postscript, output_path,\
+            "-deleteProject",  # WARNING: This will delete the project after analysis\
+        ]\
         result = subprocess.run(command, text=True, capture_output=True, check=True)
-        with open(output_path,'r') as f:
+        with open(output_path,'r') as f:\
             c_decompile = f.read()
         c_func = []
         flag = 0
-        for line in c_decompile.split('\n'):
+        for line in c_decompile.split('
+'):
             if "Function: func0" in line:#**Replace** func0 with the function name you want to decompile.
                 flag = 1
                 c_func.append(line)
@@ -108,10 +114,14 @@ with tempfile.TemporaryDirectory() as temp_dir:
             if 'func0' in c_func[idx_tmp]:
                 break
         c_func = c_func[idx_tmp:]
-        input_asm = '\n'.join(c_func).strip()
-
-        before = f"# This is the assembly code:\n"#prompt
-        after = "\n# What is the source code?\n"#prompt
+        input_asm = '
+'.join(c_func).strip()
+
+        before = f"# This is the assembly code:\
+"#prompt
+        after = "
+# What is the source code?\
+"#prompt
         input_asm_prompt = before+input_asm.strip()+after
         with open(fileName +'_' + opt +'.pseudo','w',encoding='utf-8') as f:
             f.write(input_asm_prompt)
@@ -131,8 +141,8 @@ undefined4 func0(float param_1,long param_2,int param_3)
       return 0;
     }
     while (local_28 = local_28 + 1, local_28 < param_3) {
-      if ((double)((ulong)(double)(*(float *)(param_2 + (long)local_24 * 4) -
-                                  *(float *)(param_2 + (long)local_28 * 4)) &
+      if ((double)((ulong)(double)(*(float *)(param_2 + (long)local_24 * 4) -\
+                                  *(float *)(param_2 + (long)local_28 * 4)) &\
                   SUB168(_DAT_00402010,0)) < (double)param_1) {
         return 1;
       }
@@ -162,8 +172,10 @@ c_func_decompile = tokenizer.decode(outputs[0][len(inputs[0]):-1])
 with open(fileName +'_' + OPT[0] +'.pseudo','r') as f:#original file
     func = f.read()
 
-print(f'pseudo function:\n{func}')# Note we only decompile one function, where the original file may contain multiple functions
-print(f'refined function:\n{c_func_decompile}')
+print(f'pseudo function:\
+{func}')# Note we only decompile one function, where the original file may contain multiple functions
+print(f'refined function:\
+{c_func_decompile}')
 
 ```
 
@@ -173,3 +185,15 @@ This code repository is licensed under the MIT License.
 ### 5. Contact
 
 If you have any questions, please raise an issue.
+
+## Citation
+```
+@misc{tan2024llm4decompile,
+      title={LLM4Decompile: Decompiling Binary Code with Large Language Models}, 
+      author={Hanzhuo Tan and Qi Luo and Jing Li and Yuqun Zhang},
+      year={2024},
+      eprint={2403.05286},
+      archivePrefix={arXiv},
+      primaryClass={cs.PL}
+}
+```