ejschwartz commited on
Commit
edab27e
·
1 Parent(s): d0f659d

description

Browse files
Files changed (1) hide show
  1. app.py +17 -3
app.py CHANGED
@@ -9,7 +9,22 @@ import huggingface_hub
9
 
10
  import prep_decompiled
11
 
12
- print("Hello!")
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
 
14
  hf_key = os.environ["HF_TOKEN"]
15
  huggingface_hub.login(token=hf_key)
@@ -21,8 +36,6 @@ vardecoder_model = AutoModelForCausalLM.from_pretrained(
21
  "ejschwartz/resym-vardecoder", torch_dtype=torch.bfloat16, device_map="auto"
22
  )
23
 
24
-
25
-
26
  example = """{
27
  "input": "What are the original name and data type of variables `a1`, `a2`, `k`, `j`, `i`?\n```\n_BYTE *__fastcall sub_4022CD(_BYTE *a1, __int64 a2)\n{\n_BYTE *result; // rax\n__int16 v4; // [rsp+1Ch] [rbp-14h]\nunsigned __int16 v5; // [rsp+1Eh] [rbp-12h]\nunsigned __int16 v6; // [rsp+20h] [rbp-10h]\nunsigned __int16 v7; // [rsp+22h] [rbp-Eh]\nunsigned int k; // [rsp+24h] [rbp-Ch]\nunsigned int j; // [rsp+28h] [rbp-8h]\nunsigned int i; // [rsp+2Ch] [rbp-4h]\n\nfor ( i = 0; i <= 2; ++i )\n{\nfor ( j = 0; j <= 0x3F; ++j )\n{\nfor ( k = 0; k <= 3; ++k )\n{\n*(&v4 + k) = *(_WORD *)(a2 + 2 * (k + 4 * j + ((unsigned __int64)i << 8)));\n*(&v4 + k) += (*(&v4 + k) >> 15) & 0xD01;\n*(&v4 + k) = ((((unsigned __int16)*(&v4 + k) << 10) + 1664) / 0xD01u) & 0x3FF;\n}\n*a1 = v4;\na1[1] = (4 * v5) | HIBYTE(v4);\na1[2] = (16 * v6) | (v5 >> 6);\na1[3] = ((_BYTE)v7 << 6) | (v6 >> 4);\nresult = a1 + 4;\na1[4] = v7 >> 2;\na1 += 5;\n}\n}\nreturn result;\n}\n```",
28
  "output": "a1: r, uint8_t*\na2: a, const polyvec*\nk: t, uint16_t\nj: -, -\ni: k, unsigned int",
@@ -80,5 +93,6 @@ demo = gr.Interface(
80
  gr.Textbox(lines=10, value=json.loads(example)['input']),
81
  ],
82
  outputs=gr.Text(label="Var Decoder Output"),
 
83
  )
84
  demo.launch()
 
9
 
10
  import prep_decompiled
11
 
12
+ description = """# ReSym Test Space
13
+
14
+ This is a test space of the models from the [ReSym
15
+ artifacts](https://github.com/lt-asset/resym). Sadly, at the time I am writing
16
+ this, not all of ReSym is publicly available; specifically, the Prolog component
17
+ is [not available](https://github.com/lt-asset/resym/issues/2).
18
+
19
+ This space simply performs inference on the two pretrained models available as
20
+ part of the ReSym artifacts. It takes a variable name and some decompiled code
21
+ as input, and outputs the variable type and other information.
22
+
23
+ ## Todo
24
+
25
+ * Add support for FieldDecoder model
26
+
27
+ """
28
 
29
  hf_key = os.environ["HF_TOKEN"]
30
  huggingface_hub.login(token=hf_key)
 
36
  "ejschwartz/resym-vardecoder", torch_dtype=torch.bfloat16, device_map="auto"
37
  )
38
 
 
 
39
  example = """{
40
  "input": "What are the original name and data type of variables `a1`, `a2`, `k`, `j`, `i`?\n```\n_BYTE *__fastcall sub_4022CD(_BYTE *a1, __int64 a2)\n{\n_BYTE *result; // rax\n__int16 v4; // [rsp+1Ch] [rbp-14h]\nunsigned __int16 v5; // [rsp+1Eh] [rbp-12h]\nunsigned __int16 v6; // [rsp+20h] [rbp-10h]\nunsigned __int16 v7; // [rsp+22h] [rbp-Eh]\nunsigned int k; // [rsp+24h] [rbp-Ch]\nunsigned int j; // [rsp+28h] [rbp-8h]\nunsigned int i; // [rsp+2Ch] [rbp-4h]\n\nfor ( i = 0; i <= 2; ++i )\n{\nfor ( j = 0; j <= 0x3F; ++j )\n{\nfor ( k = 0; k <= 3; ++k )\n{\n*(&v4 + k) = *(_WORD *)(a2 + 2 * (k + 4 * j + ((unsigned __int64)i << 8)));\n*(&v4 + k) += (*(&v4 + k) >> 15) & 0xD01;\n*(&v4 + k) = ((((unsigned __int16)*(&v4 + k) << 10) + 1664) / 0xD01u) & 0x3FF;\n}\n*a1 = v4;\na1[1] = (4 * v5) | HIBYTE(v4);\na1[2] = (16 * v6) | (v5 >> 6);\na1[3] = ((_BYTE)v7 << 6) | (v6 >> 4);\nresult = a1 + 4;\na1[4] = v7 >> 2;\na1 += 5;\n}\n}\nreturn result;\n}\n```",
41
  "output": "a1: r, uint8_t*\na2: a, const polyvec*\nk: t, uint16_t\nj: -, -\ni: k, unsigned int",
 
93
  gr.Textbox(lines=10, value=json.loads(example)['input']),
94
  ],
95
  outputs=gr.Text(label="Var Decoder Output"),
96
+ description=description
97
  )
98
  demo.launch()