## How to Use
Here is an example of how to use our model Note: Replace asm_func with the function that you want to decompile
Decompilation: Use falcon3-decompiler-3b to translate ghidra decompilation output to more readable code:
```python
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
import os
model_path = 'Neo111x/falcon3-decompiler-3b' # V1.5 Model
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path,torch_dtype=torch.bfloat16).cuda()
asm_func = """
char * func0(char **param_1,int param_2)
{
char **ppcVar1;
char *__s;
size_t sVar2;
int iVar3;
char *pcVar4;
pcVar4 = "";
if (0 < param_2) {
iVar3 = 0;
ppcVar1 = param_1 + (ulong)(param_2 - 1) + 1;
do {
__s = *param_1;
sVar2 = strlen(__s);
if (iVar3 < (int)sVar2) {
pcVar4 = __s;
iVar3 = (int)sVar2;
}
param_1 = param_1 + 1;
} while (param_1 != ppcVar1);
}
return pcVar4;
}
"""
before = f"# This is the assembly code:\n"#prompt
after = "\n# What is the source code?\n"#prompt
asm_func = before+asm_func.strip()+after
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, torch_dtype="auto", device_map="auto")
inputs = tokenizer(asm_func, return_tensors="pt")
with torch.no_grad():
outputs = model.generate(**inputs, max_new_tokens=2048)### max length to 4096, max new tokens should be below the range
c_func_decompile = tokenizer.decode(outputs[0][len(inputs[0]):-1])
# Note only decompile one function, where the original file may contain multiple functions
print(f'decompiled function:\n{c_func_decompile}')
```
## Contact
If you have any questions, please raise an issue.