Improve model card: Add pipeline tag, library name, update license, and correct paper link

README.md

@@ -1,33 +1,41 @@
 ---
-license: mit
+license: other
 tags:
 - decompile
 - binary
 widget:
- - text: "# This is the assembly code:\nfloat func0(float param_1)\n\n{\n  return param_1 - (float)(int)param_1;\n}# What is the source code?\n"
+- text: "# This is the assembly code:\nfloat func0(float param_1)\n\n{\n  return param_1\
+    \ - (float)(int)param_1;\n}# What is the source code?\n"
+pipeline_tag: text-generation
+library_name: transformers
 ---
 
+# LLM4Binary/llm4decompile-6.7b-v2
 
-### 1. Introduction of LLM4Decompile
+This repository hosts the **LLM4Binary/llm4decompile-6.7b-v2** model, a part of the LLM4Decompile series. This model was presented in the paper [Decompile-Bench: Million-Scale Binary-Source Function Pairs for Real-World Binary Decompilation](https://huggingface.co/papers/2505.12668).
 
-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.
+**GitHub Repository:** [LLM4Decompile](https://github.com/albertan017/LLM4Decompile)
 
-- **Github Repository:** [LLM4Decompile](https://github.com/albertan017/LLM4Decompile)
+## About LLM4Decompile
 
+LLM4Decompile is a pioneering open-source large language model dedicated to binary decompilation. Its current version supports decompiling Linux x86_64 binaries, ranging from GCC's O0 to O3 optimization levels, into human-readable C source code. The V2 series models, including `llm4decompile-6.7b-v2`, are specifically designed to **refine** the pseudo-code outputted by tools like Ghidra, having been trained on 2 billion tokens with a maximum context length of 4,096.
 
-### 2. Evaluation Results
+-   **LLM4Decompile-End** focuses on decompiling the binary directly.
+-   **LLM4Decompile-Ref** (like this `v2` model) refines the pseudo-code decompiled by Ghidra.
+
+## 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
+## How to Use
 Here is an example of how to use our model (Only for V2. For previous models, please check the corresponding model page at HF).
 
 1. Install Ghidra
@@ -95,7 +103,8 @@ with tempfile.TemporaryDirectory() as temp_dir:
             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)
@@ -111,10 +120,14 @@ 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)
@@ -165,14 +178,42 @@ 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}')
 
 ```
 
 ### 4. License
-This code repository is licensed under the MIT License.
+This code repository is licensed under the MIT and DeepSeek License.
 
 ### 5. Contact
 
 If you have any questions, please raise an issue.
+
+## Citation
+If you find this work useful, please consider citing the following papers:
+
+```bibtex
+@misc{tan2025decompilebench,
+      title={Decompile-Bench: Million-Scale Binary-Source Function Pairs for Real-World Binary Decompilation},
+      author={Hanzhuo Tan and Xiaolong Tian and Hanrui Qi and Jiaming Liu and Zuchen Gao and Siyi Wang and Qi Luo and Jing Li and Yuqun Zhang},
+      year={2025},
+      eprint={2505.12668},
+      archivePrefix={arXiv},
+      primaryClass={cs.PL},
+      url={https://arxiv.org/abs/2505.12668},
+}
+```
+
+```bibtex
+@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}
+}
+```