Spaces:
Running
Running
__0_0_0__
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +2 -0
- .vscode/settings.json +22 -0
- ADL/0/ip__urls_cords.pkl +3 -0
- ADL/1/op__is_clfd.txt +12 -0
- ADL/8/__01__.ipynb +452 -0
- ADL/_/.env +0 -0
- ADL/_/requirements.txt +2 -0
- APA/0/gemma/code_gemma__7b/.gitattributes +36 -0
- APA/0/gemma/code_gemma__7b/README.md +262 -0
- APA/0/gemma/code_gemma__7b/codegemma_nl_benchmarks.png +0 -0
- APA/0/gemma/code_gemma__7b/config.json +26 -0
- APA/0/gemma/code_gemma__7b/generation_config.json +7 -0
- APA/0/gemma/code_gemma__7b/model-00001-of-00004.safetensors +3 -0
- APA/0/gemma/code_gemma__7b/model-00002-of-00004.safetensors +3 -0
- APA/0/gemma/code_gemma__7b/model-00003-of-00004.safetensors +3 -0
- APA/0/gemma/code_gemma__7b/model-00004-of-00004.safetensors +3 -0
- APA/0/gemma/code_gemma__7b/model.safetensors.index.json +261 -0
- APA/0/gemma/code_gemma__7b/special_tokens_map.json +30 -0
- APA/0/gemma/code_gemma__7b/tokenizer.json +3 -0
- APA/0/gemma/code_gemma__7b/tokenizer.model +3 -0
- APA/0/gemma/code_gemma__7b/tokenizer_config.json +1512 -0
- APA/8/__01__.ipynb +261 -0
- APA/_/.env +0 -0
- APA/_/requirements.txt +3 -0
- BW__RGB/0/ip__img/0.jpg +0 -0
- BW__RGB/0/ip__img/1.jpg +0 -0
- BW__RGB/0/ip__img/10.jpg +0 -0
- BW__RGB/0/ip__img/100.jpg +0 -0
- BW__RGB/0/ip__img/101.jpg +0 -0
- BW__RGB/0/ip__img/102.jpg +0 -0
- BW__RGB/0/ip__img/103.jpg +0 -0
- BW__RGB/0/ip__img/104.jpg +0 -0
- BW__RGB/0/ip__img/105.jpg +0 -0
- BW__RGB/0/ip__img/106.jpg +0 -0
- BW__RGB/0/ip__img/107.jpg +0 -0
- BW__RGB/0/ip__img/108.jpg +0 -0
- BW__RGB/0/ip__img/109.jpg +0 -0
- BW__RGB/0/ip__img/11.jpg +0 -0
- BW__RGB/0/ip__img/110.jpg +0 -0
- BW__RGB/0/ip__img/111.jpg +0 -0
- BW__RGB/0/ip__img/112.jpg +0 -0
- BW__RGB/0/ip__img/113.jpg +0 -0
- BW__RGB/0/ip__img/114.jpg +0 -0
- BW__RGB/0/ip__img/115.jpg +0 -0
- BW__RGB/0/ip__img/116.jpg +0 -0
- BW__RGB/0/ip__img/117.jpg +0 -0
- BW__RGB/0/ip__img/118.jpg +0 -0
- BW__RGB/0/ip__img/119.jpg +0 -0
- BW__RGB/0/ip__img/12.jpg +0 -0
- BW__RGB/0/ip__img/120.jpg +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
APA/0/gemma/code_gemma__7b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
37 |
+
PUP/0/datum/datum__phishing.csv filter=lfs diff=lfs merge=lfs -text
|
.vscode/settings.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"terminal.integrated.env.windows": {
|
3 |
+
"PATH": "${.env:PATH};C:/Windows/System32;%SystemRoot%/System32/Wbem;${workspaceFolder}/__/conda/Miniconda/win__x64/__0_0_0__/Scripts"
|
4 |
+
},
|
5 |
+
"terminal.integrated.profiles.windows": {
|
6 |
+
"ps1__conda__win64": {
|
7 |
+
"overrideName" : true,
|
8 |
+
"source": "PowerShell",
|
9 |
+
"args": [
|
10 |
+
"-ExecutionPolicy",
|
11 |
+
"ByPass",
|
12 |
+
"-NoExit",
|
13 |
+
"-Command",
|
14 |
+
"& ${workspaceFolder}/__/conda/Miniconda/win__x64/__0_0_0__/shell/condabin/conda-hook.ps1",
|
15 |
+
]
|
16 |
+
}
|
17 |
+
},
|
18 |
+
"terminal.integrated.defaultProfile.windows": "ps1__conda__win64",
|
19 |
+
|
20 |
+
"python.defaultInterpreterPath": "${workspaceFolder}/__/conda/Miniconda/win__x64/__0_0_0__/python.exe",
|
21 |
+
"python.terminal.activateEnvironment": true
|
22 |
+
}
|
ADL/0/ip__urls_cords.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17b718e0fb8c4e4936fe1a748ea4bdf301ce3f640eab93d77693d7dd9e278308
|
3 |
+
size 355422
|
ADL/1/op__is_clfd.txt
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
ip :: ['http://www.shea-davis.net/qKs1wmFu0jHdX7gAoX1WE1tv69bSdk9Jkhu0WsIpmPc3VaoI2pZbgRVuAFq1pa1Tb38tYleLhyGjWR?param_1=0UxBOdKj5br0V2Cc2FnjazaehJCXjz4j¶m_2=L0Dn9ih6RCn72UtzdwpUYPUWoIl33D7OJOeMdfwjsQ8inUgfpomkSo3Hh95o1¶m_3=KeF3EtmZ0ggJQCmVc9C1zhZZF26Pvq0uOHXTvA6AD0EIKpEjqlY7', (529475, 363074)]
|
3 |
+
op :: 1
|
4 |
+
|
5 |
+
ip :: ['http://www.ads.norton.com/LStKS8AZjsfm6pbT63O9baOtU1TCmJedJDvpR9WIRSZf4JBh5olBEAwn940PgK?param_1=6MrVuvl40jBNREhnFiiTQVMFPwFnUqqG9GufiKxPKsPEn9C4U13THBfDW1ix8¶m_2=DQ0ZSCv8NWiLKSJsYPacqE1mYI5KHvMFjSZbX37tjSlFkouZhXaQRWJ81Zj1ZCs24lOmvGBFW¶m_3=wElK6BbQf0epdFQ5wRCCJDCduBr¶m_4=IAcf6ylq8m4n4zC93NLh4g103YZJdEXkySuhdDdB7ZqkdmaPZSUTtQCnFBU4¶m_5=OOxQ18iw22ALICZaw9EavJgxfFUR5XNLCmZeayodPmGQvtTbJ8lix¶m_6=3XIQ7fnNpwIrttMEekk6dtegXOBmgesqlAA5HBgn9NScqNS3yU1Oe0A2fJ9o81HVeuUMbocC3', (294620, 518935)]
|
6 |
+
op :: 0
|
7 |
+
|
8 |
+
ip :: ['http://www.shea-davis.net/qKs1wmFu0jHdX7gAoX1WE1tv69bSdk9Jkhu0WsIpmPc3VaoI2pZbgRVuAFq1pa1Tb38tYleLhyGjWR?param_1=0UxBOdKj5br0V2Cc2FnjazaehJCXjz4j¶m_2=L0Dn9ih6RCn72UtzdwpUYPUWoIl33D7OJOeMdfwjsQ8inUgfpomkSo3Hh95o1¶m_3=KeF3EtmZ0ggJQCmVc9C1zhZZF26Pvq0uOHXTvA6AD0EIKpEjqlY7', (529475, 363074)]
|
9 |
+
op :: 1
|
10 |
+
|
11 |
+
ip :: ['http://www.ads.norton.com/LStKS8AZjsfm6pbT63O9baOtU1TCmJedJDvpR9WIRSZf4JBh5olBEAwn940PgK?param_1=6MrVuvl40jBNREhnFiiTQVMFPwFnUqqG9GufiKxPKsPEn9C4U13THBfDW1ix8¶m_2=DQ0ZSCv8NWiLKSJsYPacqE1mYI5KHvMFjSZbX37tjSlFkouZhXaQRWJ81Zj1ZCs24lOmvGBFW¶m_3=wElK6BbQf0epdFQ5wRCCJDCduBr¶m_4=IAcf6ylq8m4n4zC93NLh4g103YZJdEXkySuhdDdB7ZqkdmaPZSUTtQCnFBU4¶m_5=OOxQ18iw22ALICZaw9EavJgxfFUR5XNLCmZeayodPmGQvtTbJ8lix¶m_6=3XIQ7fnNpwIrttMEekk6dtegXOBmgesqlAA5HBgn9NScqNS3yU1Oe0A2fJ9o81HVeuUMbocC3', (294620, 518935)]
|
12 |
+
op :: 1
|
ADL/8/__01__.ipynb
ADDED
@@ -0,0 +1,452 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"cell_type": "markdown",
|
5 |
+
"metadata": {},
|
6 |
+
"source": [
|
7 |
+
"---"
|
8 |
+
]
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"cell_type": "markdown",
|
12 |
+
"metadata": {},
|
13 |
+
"source": [
|
14 |
+
"> <center><a href='https://o-0268-kvnaditya-8620-o.web.app/documentation/adl.html'><h3>Implementation of Ad-Sherlock for Click-Fraud Detection using Deep-Learning</h3></center></a>\n",
|
15 |
+
"> <hr>\n",
|
16 |
+
"> <center>{K.V.N.Aditya | T.Vaishnavi Sagar | K.Karthik}</center>\n",
|
17 |
+
"> <br>\n",
|
18 |
+
"> <center>CMR Technical Campus</center>"
|
19 |
+
]
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"cell_type": "markdown",
|
23 |
+
"metadata": {},
|
24 |
+
"source": [
|
25 |
+
"---\n",
|
26 |
+
"---"
|
27 |
+
]
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"cell_type": "markdown",
|
31 |
+
"metadata": {},
|
32 |
+
"source": [
|
33 |
+
"### <center>importing modules</center>"
|
34 |
+
]
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"cell_type": "code",
|
38 |
+
"execution_count": null,
|
39 |
+
"metadata": {},
|
40 |
+
"outputs": [],
|
41 |
+
"source": [
|
42 |
+
"import random\n",
|
43 |
+
"import string\n",
|
44 |
+
"import os\n",
|
45 |
+
"import pickle\n",
|
46 |
+
"import torch\n",
|
47 |
+
"import warnings\n",
|
48 |
+
"from faker import Faker\n",
|
49 |
+
"from torch import nn"
|
50 |
+
]
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"cell_type": "markdown",
|
54 |
+
"metadata": {},
|
55 |
+
"source": [
|
56 |
+
"---"
|
57 |
+
]
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"cell_type": "markdown",
|
61 |
+
"metadata": {},
|
62 |
+
"source": [
|
63 |
+
"### <center>initializing path</center>"
|
64 |
+
]
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"cell_type": "code",
|
68 |
+
"execution_count": null,
|
69 |
+
"metadata": {},
|
70 |
+
"outputs": [],
|
71 |
+
"source": [
|
72 |
+
"DMA__ADL = os.path.abspath('../../ADL').replace('\\\\', '/')"
|
73 |
+
]
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"cell_type": "markdown",
|
77 |
+
"metadata": {},
|
78 |
+
"source": [
|
79 |
+
"---"
|
80 |
+
]
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"cell_type": "markdown",
|
84 |
+
"metadata": {},
|
85 |
+
"source": [
|
86 |
+
"### <center>configuring 'ipynb' and exploring GPU info</center>"
|
87 |
+
]
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"cell_type": "code",
|
91 |
+
"execution_count": null,
|
92 |
+
"metadata": {},
|
93 |
+
"outputs": [],
|
94 |
+
"source": [
|
95 |
+
"warnings.filterwarnings(\"ignore\")\n",
|
96 |
+
"print(f'count of gpu devices : `{torch.cuda.device_count()}`')\n",
|
97 |
+
"print(f'id of gpu device : `{torch.cuda.current_device()}`')\n",
|
98 |
+
"print(f'is cuda available : `{torch.cuda.is_available()}`')\n",
|
99 |
+
"print(f'is cuda enabled at backend : `{torch.backends.cudnn.enabled}`')\n",
|
100 |
+
"print(f'name of the instance gpu device : `{torch.cuda.get_device_name(torch.cuda.current_device())}`')\n",
|
101 |
+
"print(f'version of cuda : `{torch.backends.cudnn.version()}`')"
|
102 |
+
]
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"cell_type": "markdown",
|
106 |
+
"metadata": {},
|
107 |
+
"source": [
|
108 |
+
"---"
|
109 |
+
]
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"cell_type": "markdown",
|
113 |
+
"metadata": {},
|
114 |
+
"source": [
|
115 |
+
"### <center>initializing data</center>"
|
116 |
+
]
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"cell_type": "code",
|
120 |
+
"execution_count": null,
|
121 |
+
"metadata": {},
|
122 |
+
"outputs": [],
|
123 |
+
"source": [
|
124 |
+
"print(\"--------\")\n",
|
125 |
+
"print(\"IPO\")\n",
|
126 |
+
"io_pklio0uc = f'{DMA__ADL}/0/ip__urls_cords.pkl'\n",
|
127 |
+
"def func_io_sudo_urls_cords(n=4*random.randrange(20,80)):\n",
|
128 |
+
" random.seed(268862)\n",
|
129 |
+
" Faker.seed(268862)\n",
|
130 |
+
" fake = Faker()\n",
|
131 |
+
" sudo_urls = [f'http://www.ads.{fake.domain_name()}' for _ in range(n//4)] + [f'https://www.ads.{fake.domain_name()}' for _ in range(n//4)] + [f'http://www.{fake.domain_name()}' for _ in range(n//4)] + [f'https://www.{fake.domain_name()}' for _ in range(n//4)]\n",
|
132 |
+
" sudo_urls = [sudo_urls[P]+'/'+ ''.join(random.choice(random.choice(string.digits + string.ascii_letters)) for _ in range(random.randint(20, 80))) + '?' + '&'.join([f\"param_{p}={''.join(random.choice(random.choice(string.digits + string.ascii_letters)) for _ in range(random.randint(20, 80)))}\" for p in range(1, random.randint(2, 8) + 1)]) for P in range(len(sudo_urls))]\n",
|
133 |
+
" random.shuffle(sudo_urls)\n",
|
134 |
+
" sudo_isad = [1 if('ad' in i) else 0 for i in sudo_urls]\n",
|
135 |
+
" sudo_cords = [(random.randrange(2,862268),random.randrange(2,862268)) for _ in range(n)]\n",
|
136 |
+
" random.shuffle(sudo_cords)\n",
|
137 |
+
" sudo_urls_cords = [(sudo_urls[p],(sudo_cords[p][0],sudo_cords[p][1]),sudo_isad[p]) for p in range(n)]\n",
|
138 |
+
" random.shuffle(sudo_urls_cords)\n",
|
139 |
+
" return sudo_urls_cords\n",
|
140 |
+
"if(not os.path.exists(io_pklio0uc)):\n",
|
141 |
+
" io__sudo_urls_cords = func_io_sudo_urls_cords(888) # n : multiples of '4'\n",
|
142 |
+
" pickle.dump(io__sudo_urls_cords, open(io_pklio0uc, 'wb'))\n",
|
143 |
+
"io__sudo_urls_cords = pickle.load(open(io_pklio0uc, 'rb'))\n",
|
144 |
+
"io__sudo_urls = [p[0] for p in io__sudo_urls_cords]\n",
|
145 |
+
"io__sudo_cord_x,io__sudo_cord_y = [p[1][0] for p in io__sudo_urls_cords],[p[1][1] for p in io__sudo_urls_cords]\n",
|
146 |
+
"io__sudo_isad = [p[2] for p in io__sudo_urls_cords]\n",
|
147 |
+
"for p in random.sample(io__sudo_urls_cords,4):\n",
|
148 |
+
" print(p)\n",
|
149 |
+
"print(\"--------\")"
|
150 |
+
]
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"cell_type": "markdown",
|
154 |
+
"metadata": {},
|
155 |
+
"source": [
|
156 |
+
"---"
|
157 |
+
]
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"cell_type": "markdown",
|
161 |
+
"metadata": {},
|
162 |
+
"source": [
|
163 |
+
"### <center>converting the data into tensors</center>"
|
164 |
+
]
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"cell_type": "code",
|
168 |
+
"execution_count": null,
|
169 |
+
"metadata": {},
|
170 |
+
"outputs": [],
|
171 |
+
"source": [
|
172 |
+
"io__sudo_urls = torch.tensor([[ord(p) for p in io] + [(-1)*len(io)]*(862 - len(io)) for io in io__sudo_urls]).to(torch.float).cuda(torch.cuda.current_device())\n",
|
173 |
+
"io__sudo_cord_x = torch.tensor(io__sudo_cord_x).cuda(torch.cuda.current_device())\n",
|
174 |
+
"io__sudo_cord_y = torch.tensor(io__sudo_cord_y).cuda(torch.cuda.current_device())\n",
|
175 |
+
"io__sudo_cords = torch.stack((io__sudo_cord_x,io__sudo_cord_y),dim=1).cuda(torch.cuda.current_device())\n",
|
176 |
+
"io__sudo_isad = torch.tensor(io__sudo_isad).cuda(torch.cuda.current_device())"
|
177 |
+
]
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"cell_type": "markdown",
|
181 |
+
"metadata": {},
|
182 |
+
"source": [
|
183 |
+
"---"
|
184 |
+
]
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"cell_type": "markdown",
|
188 |
+
"metadata": {},
|
189 |
+
"source": [
|
190 |
+
"### <center>defining Neural Network</center>"
|
191 |
+
]
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"cell_type": "code",
|
195 |
+
"execution_count": null,
|
196 |
+
"metadata": {},
|
197 |
+
"outputs": [],
|
198 |
+
"source": [
|
199 |
+
"class __01__(nn.Module):\n",
|
200 |
+
" def __init__(IO):\n",
|
201 |
+
" super().__init__()\n",
|
202 |
+
" IO._O_ = torch.zeros(1).unsqueeze(0).to(torch.float).cuda(torch.cuda.current_device())\n",
|
203 |
+
" IO._I_ = torch.ones(1).unsqueeze(0).to(torch.float).cuda(torch.cuda.current_device())\n",
|
204 |
+
" IO.l20 = nn.Linear(862,1)\n",
|
205 |
+
" IO.l21 = nn.Linear(2,1)\n",
|
206 |
+
" IO.l30 = nn.Bilinear(1,1,1)\n",
|
207 |
+
" IO.l31 = nn.Bilinear(1,1,1)\n",
|
208 |
+
" IO.l40 = nn.Identity()\n",
|
209 |
+
" IO.l41 = nn.Identity() \n",
|
210 |
+
" IO.l5 = nn.Sigmoid()\n",
|
211 |
+
" IO.h20 = torch.zeros(1).unsqueeze(0).to(torch.float).cuda(torch.cuda.current_device())\n",
|
212 |
+
" IO.h21 = torch.zeros(1).unsqueeze(0).to(torch.float).cuda(torch.cuda.current_device())\n",
|
213 |
+
" IO.h22 = torch.zeros(1).unsqueeze(0).to(torch.float).cuda(torch.cuda.current_device())\n",
|
214 |
+
" IO.h23 = torch.zeros(1).unsqueeze(0).to(torch.float).cuda(torch.cuda.current_device())\n",
|
215 |
+
" IO.h30 = torch.zeros(1).unsqueeze(0).to(torch.float).cuda(torch.cuda.current_device())\n",
|
216 |
+
" IO.h31 = torch.zeros(1).unsqueeze(0).to(torch.float).cuda(torch.cuda.current_device())\n",
|
217 |
+
" def __8__(IO,ip=['',(0,0)],op=0.5):\n",
|
218 |
+
" IO.ip = ip\n",
|
219 |
+
" IO.h00 = IO.ip\n",
|
220 |
+
" IO.h10 = IO.l20(IO.h00[0].to(torch.float)).unsqueeze(0)\n",
|
221 |
+
" IO.h11 = IO.l21(IO.h00[1].to(torch.float)).unsqueeze(0)\n",
|
222 |
+
" IO.h20[op==0 or op==0.5] = IO.l30(IO.h20,IO.h10)\n",
|
223 |
+
" IO.h21[op==0.5 or op==1] = IO.l30(IO.h21,IO.h10)\n",
|
224 |
+
" IO.h22[op==0 or op==0.5] = IO.l31(IO.h22,IO.h11)\n",
|
225 |
+
" IO.h23[op==0.5 or op==1] = IO.l31(IO.h23,IO.h11)\n",
|
226 |
+
" IO.h30[op==0] = IO.l40(torch.max(IO.h20,IO._O_))\n",
|
227 |
+
" IO.h30[op==0.5] = IO.l40(torch.max(IO.h20,IO.h21))\n",
|
228 |
+
" IO.h30[op==1] = IO.l40(torch.max(IO.h21,IO._O_))\n",
|
229 |
+
" IO.h31[op==0] = IO.l41(torch.max(IO.h22,IO._O_))\n",
|
230 |
+
" IO.h31[op==0.5] = IO.l41(torch.max(IO.h22,IO.h23))\n",
|
231 |
+
" IO.h31[op==1] = IO.l41(torch.max(IO.h23,IO._O_))\n",
|
232 |
+
" IO.h40 = IO.l5(torch.mean(torch.stack((IO.h30,IO.h31)))).item()\n",
|
233 |
+
" IO.op = int(IO.h40 > 0.5)\n",
|
234 |
+
" return(IO.op)"
|
235 |
+
]
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"cell_type": "markdown",
|
239 |
+
"metadata": {},
|
240 |
+
"source": [
|
241 |
+
"---"
|
242 |
+
]
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"cell_type": "markdown",
|
246 |
+
"metadata": {},
|
247 |
+
"source": [
|
248 |
+
"### <center>defining the pipeline of `ADL` model to predict 'is_clfd' and to save the prediction</center>"
|
249 |
+
]
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"cell_type": "code",
|
253 |
+
"execution_count": null,
|
254 |
+
"metadata": {},
|
255 |
+
"outputs": [],
|
256 |
+
"source": [
|
257 |
+
"def func__is_clfd(ip):\n",
|
258 |
+
" _01_ = __01__().cuda(torch.cuda.current_device())\n",
|
259 |
+
" ip_url = torch.tensor([ord(p) for p in ip[0]] + [(-1)*len(ip[0])]*(862 - len(ip[0]))).to(torch.float).cuda(torch.cuda.current_device())\n",
|
260 |
+
" ip_cordx = torch.tensor(ip[1][0]).cuda(torch.cuda.current_device())\n",
|
261 |
+
" ip_cordy = torch.tensor(ip[1][1]).cuda(torch.cuda.current_device())\n",
|
262 |
+
" ip_cords = torch.stack((ip_cordx,ip_cordy),dim=0).cuda(torch.cuda.current_device())\n",
|
263 |
+
" op = _01_.__8__(ip=[ip_url,ip_cords])\n",
|
264 |
+
" with open(f'{DMA__ADL}/1/op__is_clfd.txt','a') as f:\n",
|
265 |
+
" f.write('\\n')\n",
|
266 |
+
" f.write(f\"ip :: {ip}\")\n",
|
267 |
+
" f.write('\\n')\n",
|
268 |
+
" f.write(f'op :: {op}')\n",
|
269 |
+
" f.write('\\n')\n",
|
270 |
+
" return op"
|
271 |
+
]
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"cell_type": "markdown",
|
275 |
+
"metadata": {},
|
276 |
+
"source": [
|
277 |
+
"---"
|
278 |
+
]
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"cell_type": "markdown",
|
282 |
+
"metadata": {},
|
283 |
+
"source": [
|
284 |
+
"### <center>initializing Neural Network</center>"
|
285 |
+
]
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"cell_type": "code",
|
289 |
+
"execution_count": null,
|
290 |
+
"metadata": {},
|
291 |
+
"outputs": [],
|
292 |
+
"source": [
|
293 |
+
"_01_ = __01__().cuda(torch.cuda.current_device())\n",
|
294 |
+
"print(_01_)"
|
295 |
+
]
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"cell_type": "markdown",
|
299 |
+
"metadata": {},
|
300 |
+
"source": [
|
301 |
+
"---"
|
302 |
+
]
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"cell_type": "markdown",
|
306 |
+
"metadata": {},
|
307 |
+
"source": [
|
308 |
+
"### <center>exploring the `ADL` model</center>"
|
309 |
+
]
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"cell_type": "code",
|
313 |
+
"execution_count": null,
|
314 |
+
"metadata": {},
|
315 |
+
"outputs": [],
|
316 |
+
"source": [
|
317 |
+
"dct__01_wb = {}\n",
|
318 |
+
"for i,j in _01_.named_parameters():\n",
|
319 |
+
" dct__01_wb[i] = j.mean().item()\n",
|
320 |
+
" print(i,j.mean().item())"
|
321 |
+
]
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"cell_type": "markdown",
|
325 |
+
"metadata": {},
|
326 |
+
"source": [
|
327 |
+
"---"
|
328 |
+
]
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"cell_type": "markdown",
|
332 |
+
"metadata": {},
|
333 |
+
"source": [
|
334 |
+
"### <center>initializing the train, test and validation of the data</center>"
|
335 |
+
]
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"cell_type": "code",
|
339 |
+
"execution_count": null,
|
340 |
+
"metadata": {},
|
341 |
+
"outputs": [],
|
342 |
+
"source": [
|
343 |
+
"lip0,lip1,lop0,lop1,lio0,lio1 = [],[],[],[],[],[]\n",
|
344 |
+
"for n in range(0,666):\n",
|
345 |
+
" lip0.append(_01_.__8__(ip=[io__sudo_urls[n],io__sudo_cords[n]],op=io__sudo_isad[n].__int__()))\n",
|
346 |
+
" lip1.append(io__sudo_isad[n].__int__())\n",
|
347 |
+
"for n in range(666,888):\n",
|
348 |
+
" lop0.append(_01_.__8__(ip=[io__sudo_urls[n],io__sudo_cords[n]]))\n",
|
349 |
+
" lop1.append(io__sudo_isad[n].__int__())\n",
|
350 |
+
"for n in range(0,888):\n",
|
351 |
+
" lio0.append(_01_.__8__(ip=[io__sudo_urls[n],io__sudo_cords[n]]))\n",
|
352 |
+
" lio1.append(io__sudo_isad[n].__int__())"
|
353 |
+
]
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"cell_type": "code",
|
357 |
+
"execution_count": null,
|
358 |
+
"metadata": {},
|
359 |
+
"outputs": [],
|
360 |
+
"source": [
|
361 |
+
"print(f\"training instances : (666) :\\n\\t:: no. of instances pridicted as 'click-fraud' : {sum(lip0)}\\n\\t:: no. of instances actually 'click-fraud' : {sum(lip1)}\\n\\t:: percent of pridiction of 'click-fraud' : {sum(lip0)/sum(lip1)*100}\")\n",
|
362 |
+
"print(f\"testing instances : (222) :\\n\\t:: no. of instances pridicted as 'click-fraud' : {sum(lop0)}\\n\\t:: no. of instances actually 'click-fraud' : {sum(lop1)}\\n\\t:: percent of pridiction of 'click-fraud' : {sum(lop0)/sum(lop1)*100}\")\n",
|
363 |
+
"print(f\"overall instances : (888) :\\n\\t:: no. of instances pridicted as 'click-fraud' : {sum(lio0)}\\n\\t:: no. of instances actually 'click-fraud' : {sum(lio1)}\\n\\t:: percent of pridiction of 'click-fraud' : {sum(lio0)/sum(lio1)*100}\")"
|
364 |
+
]
|
365 |
+
},
|
366 |
+
{
|
367 |
+
"cell_type": "markdown",
|
368 |
+
"metadata": {},
|
369 |
+
"source": [
|
370 |
+
"---"
|
371 |
+
]
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"cell_type": "markdown",
|
375 |
+
"metadata": {},
|
376 |
+
"source": [
|
377 |
+
"### <center>evaluating the `ADL` model based on a random input data instance [url,cords] and predicting the output [is_clfd]</center>"
|
378 |
+
]
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"cell_type": "code",
|
382 |
+
"execution_count": null,
|
383 |
+
"metadata": {},
|
384 |
+
"outputs": [],
|
385 |
+
"source": [
|
386 |
+
"io = _01_.__8__(ip=[io__sudo_urls[random.choice(range(0,889))],io__sudo_cords[random.choice(range(0,889))]])\n",
|
387 |
+
"print(f\"evaluating a random instance :: [index] : `{random.choice(range(0,889))+1}` :\",end=\"\\n\\t:: \")\n",
|
388 |
+
"print(f'predicted output :: {io} || actual output :: {io__sudo_isad[random.choice(range(0,889))].__int__()}')"
|
389 |
+
]
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"cell_type": "markdown",
|
393 |
+
"metadata": {},
|
394 |
+
"source": [
|
395 |
+
"---"
|
396 |
+
]
|
397 |
+
},
|
398 |
+
{
|
399 |
+
"cell_type": "markdown",
|
400 |
+
"metadata": {},
|
401 |
+
"source": [
|
402 |
+
"### <center>predicting the click-fraud for the input by passing into the defined pipeline</center>"
|
403 |
+
]
|
404 |
+
},
|
405 |
+
{
|
406 |
+
"cell_type": "code",
|
407 |
+
"execution_count": null,
|
408 |
+
"metadata": {},
|
409 |
+
"outputs": [],
|
410 |
+
"source": [
|
411 |
+
"ip = ['http://www.shea-davis.net/qKs1wmFu0jHdX7gAoX1WE1tv69bSdk9Jkhu0WsIpmPc3VaoI2pZbgRVuAFq1pa1Tb38tYleLhyGjWR?param_1=0UxBOdKj5br0V2Cc2FnjazaehJCXjz4j¶m_2=L0Dn9ih6RCn72UtzdwpUYPUWoIl33D7OJOeMdfwjsQ8inUgfpomkSo3Hh95o1¶m_3=KeF3EtmZ0ggJQCmVc9C1zhZZF26Pvq0uOHXTvA6AD0EIKpEjqlY7',(529475, 363074)]\n",
|
412 |
+
"op = func__is_clfd(ip)\n",
|
413 |
+
"print(f\"ip__url : {ip[0]}\\nip__cords : {ip[1]}\")\n",
|
414 |
+
"print(f'predicted output :: {op}')\n",
|
415 |
+
"print(\"--------\")\n",
|
416 |
+
"ip = ['http://www.ads.norton.com/LStKS8AZjsfm6pbT63O9baOtU1TCmJedJDvpR9WIRSZf4JBh5olBEAwn940PgK?param_1=6MrVuvl40jBNREhnFiiTQVMFPwFnUqqG9GufiKxPKsPEn9C4U13THBfDW1ix8¶m_2=DQ0ZSCv8NWiLKSJsYPacqE1mYI5KHvMFjSZbX37tjSlFkouZhXaQRWJ81Zj1ZCs24lOmvGBFW¶m_3=wElK6BbQf0epdFQ5wRCCJDCduBr¶m_4=IAcf6ylq8m4n4zC93NLh4g103YZJdEXkySuhdDdB7ZqkdmaPZSUTtQCnFBU4¶m_5=OOxQ18iw22ALICZaw9EavJgxfFUR5XNLCmZeayodPmGQvtTbJ8lix¶m_6=3XIQ7fnNpwIrttMEekk6dtegXOBmgesqlAA5HBgn9NScqNS3yU1Oe0A2fJ9o81HVeuUMbocC3',(294620, 518935)]\n",
|
417 |
+
"op = func__is_clfd(ip)\n",
|
418 |
+
"print(f\"ip__url : {ip[0]}\\nip__cords : {ip[1]}\")\n",
|
419 |
+
"print(f'predicted output :: {op}')"
|
420 |
+
]
|
421 |
+
},
|
422 |
+
{
|
423 |
+
"cell_type": "markdown",
|
424 |
+
"metadata": {},
|
425 |
+
"source": [
|
426 |
+
"---"
|
427 |
+
]
|
428 |
+
}
|
429 |
+
],
|
430 |
+
"metadata": {
|
431 |
+
"kernelspec": {
|
432 |
+
"display_name": "Python 3",
|
433 |
+
"language": "python",
|
434 |
+
"name": "python3"
|
435 |
+
},
|
436 |
+
"language_info": {
|
437 |
+
"codemirror_mode": {
|
438 |
+
"name": "ipython",
|
439 |
+
"version": 3
|
440 |
+
},
|
441 |
+
"file_extension": ".py",
|
442 |
+
"mimetype": "text/x-python",
|
443 |
+
"name": "python",
|
444 |
+
"nbconvert_exporter": "python",
|
445 |
+
"pygments_lexer": "ipython3",
|
446 |
+
"version": "3.12.1"
|
447 |
+
},
|
448 |
+
"orig_nbformat": 4
|
449 |
+
},
|
450 |
+
"nbformat": 4,
|
451 |
+
"nbformat_minor": 2
|
452 |
+
}
|
ADL/_/.env
ADDED
File without changes
|
ADL/_/requirements.txt
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
1 |
+
Faker==24.9.0
|
2 |
+
torch==2.2.2+cu121
|
APA/0/gemma/code_gemma__7b/.gitattributes
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
APA/0/gemma/code_gemma__7b/README.md
ADDED
@@ -0,0 +1,262 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
extra_gated_heading: Access CodeGemma on Hugging Face
|
4 |
+
extra_gated_prompt: >-
|
5 |
+
To access CodeGemma on Hugging Face, you’re required to review and agree to
|
6 |
+
Google’s usage license. To do this, please ensure you’re logged-in to Hugging
|
7 |
+
Face and click below. Requests are processed immediately.
|
8 |
+
extra_gated_button_content: Acknowledge license
|
9 |
+
license: gemma
|
10 |
+
license_link: https://ai.google.dev/gemma/terms
|
11 |
+
---
|
12 |
+
|
13 |
+
# CodeGemma
|
14 |
+
|
15 |
+
Model Page
|
16 |
+
: [CodeGemma](https://ai.google.dev/gemma/docs/codegemma)
|
17 |
+
|
18 |
+
Resources and Technical Documentation
|
19 |
+
: [Technical Report](https://goo.gle/codegemma)
|
20 |
+
: [Responsible Generative AI Toolkit](https://ai.google.dev/responsible)
|
21 |
+
|
22 |
+
Terms of Use
|
23 |
+
: [Terms](https://ai.google.dev/gemma/terms)
|
24 |
+
|
25 |
+
Authors
|
26 |
+
: Google
|
27 |
+
|
28 |
+
## Model Information
|
29 |
+
|
30 |
+
Summary description and brief definition of inputs and outputs.
|
31 |
+
|
32 |
+
### Description
|
33 |
+
|
34 |
+
CodeGemma is a collection of lightweight open code models built on top of Gemma. CodeGemma models are text-to-text and text-to-code decoder-only models and are available as a 7 billion pretrained variant that specializes in code completion and code generation tasks, a 7 billion parameter instruction-tuned variant for code chat and instruction following and a 2 billion parameter pretrained variant for fast code completion.
|
35 |
+
|
36 |
+
| | [codegemma-2b](https://huggingface.co/google/codegemma-2b) | [**codegemma-7b**](https://huggingface.co/google/codegemma-7b) | [codegemma-7b-it](https://huggingface.co/google/codegemma-7b-it) |
|
37 |
+
|----------------------------------|:----------------------------------------------------------------:|:----------------------------------------------------------:|:----------------------------------------------------------------:|
|
38 |
+
| Code Completion | ✅ | ✅ | |
|
39 |
+
| Generation from natural language | | ✅ | ✅ |
|
40 |
+
| Chat | | | ✅ |
|
41 |
+
| Instruction Following | | | ✅ |
|
42 |
+
|
43 |
+
### Sample Usage
|
44 |
+
|
45 |
+
#### For Code Completion
|
46 |
+
|
47 |
+
Code completion can be used for infilling inside code editors. CodeGemma was trained for this task using the fill-in-the-middle (FIM) objective, where you provide a prefix and a suffix as context for the completion. The following tokens are used to separate the different parts of the input:
|
48 |
+
|
49 |
+
- `<|fim_prefix|>` precedes the context before the completion we want to run.
|
50 |
+
- `<|fim_suffix|>` precedes the suffix. You must put this token exactly where the cursor would be positioned in an editor, as this is the location that will be completed by the model.
|
51 |
+
- `<|fim_middle|>` is the prompt that invites the model to run the generation.
|
52 |
+
|
53 |
+
In addition to these, there's also `<|file_separator|>`, which is used to provide multi-file contexts.
|
54 |
+
|
55 |
+
Please, make sure to not provide any extra spaces or newlines around the tokens, other than those that would naturally occur in the code fragment you want to complete. Here's an example:
|
56 |
+
|
57 |
+
```python
|
58 |
+
from transformers import GemmaTokenizer, AutoModelForCausalLM
|
59 |
+
|
60 |
+
model_id = "google/codegemma-7b"
|
61 |
+
tokenizer = GemmaTokenizer.from_pretrained(model_id)
|
62 |
+
model = AutoModelForCausalLM.from_pretrained(model_id)
|
63 |
+
|
64 |
+
prompt = '''\
|
65 |
+
<|fim_prefix|>import datetime
|
66 |
+
def calculate_age(birth_year):
|
67 |
+
"""Calculates a person's age based on their birth year."""
|
68 |
+
current_year = datetime.date.today().year
|
69 |
+
<|fim_suffix|>
|
70 |
+
return age<|fim_middle|>\
|
71 |
+
'''
|
72 |
+
|
73 |
+
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
74 |
+
prompt_len = inputs["input_ids"].shape[-1]
|
75 |
+
outputs = model.generate(**inputs, max_new_tokens=100)
|
76 |
+
print(tokenizer.decode(outputs[0][prompt_len:]))
|
77 |
+
```
|
78 |
+
|
79 |
+
This may return something like the following:
|
80 |
+
|
81 |
+
```
|
82 |
+
age = current_year - birth_year<|file_separator|>test_calculate_age.py
|
83 |
+
<|fim_suffix|>
|
84 |
+
assert calculate_age(1990) == 33
|
85 |
+
assert calculate_age(1980) == 43
|
86 |
+
assert calculate_age(1970) == 53
|
87 |
+
assert calculate_age(1960) == 63
|
88 |
+
assert calculate_age(1950) == 73
|
89 |
+
```
|
90 |
+
|
91 |
+
Note the extra content after the correct completion. The model returns the completion, followed by one of the FIM tokens or the EOS token. You should ignore everything that comes after any of these tokens. A good way to achieve this is by providing a list of terminators to the `generate` function, like this:
|
92 |
+
|
93 |
+
```python
|
94 |
+
FIM_PREFIX = '<|fim_prefix|>'
|
95 |
+
FIM_SUFFIX = '<|fim_suffix|>'
|
96 |
+
FIM_MIDDLE = '<|fim_middle|>'
|
97 |
+
FIM_FILE_SEPARATOR = '<|file_separator|>'
|
98 |
+
|
99 |
+
terminators = tokenizer.convert_tokens_to_ids([FIM_PREFIX, FIM_MIDDLE, FIM_SUFFIX, FIM_FILE_SEPARATOR])
|
100 |
+
terminators += [tokenizer.eos_token_id]
|
101 |
+
|
102 |
+
outputs = model.generate(
|
103 |
+
**inputs,
|
104 |
+
max_new_tokens=100,
|
105 |
+
eos_token_id=terminators,
|
106 |
+
)
|
107 |
+
```
|
108 |
+
|
109 |
+
In this case, generation stops as soon as the first delimiter is found in the response:
|
110 |
+
|
111 |
+
```
|
112 |
+
age = current_year - birth_year<|file_separator|>
|
113 |
+
```
|
114 |
+
|
115 |
+
|
116 |
+
#### For Code Generation
|
117 |
+
|
118 |
+
```python
|
119 |
+
from transformers import GemmaTokenizer, AutoModelForCausalLM
|
120 |
+
|
121 |
+
tokenizer = GemmaTokenizer.from_pretrained("google/codegemma-7b")
|
122 |
+
model = AutoModelForCausalLM.from_pretrained("google/codegemma-7b")
|
123 |
+
|
124 |
+
input_text = "Write me a Python function to calculate the nth fibonacci number."
|
125 |
+
input_ids = tokenizer(input_text, return_tensors="pt")
|
126 |
+
|
127 |
+
outputs = model.generate(**input_ids)
|
128 |
+
print(tokenizer.decode(outputs[0]))
|
129 |
+
```
|
130 |
+
|
131 |
+
### Inputs and Outputs
|
132 |
+
|
133 |
+
Inputs
|
134 |
+
: For pretrained model variants: code prefix and/or suffix for code completion and generation scenarios, or natural language text or prompt
|
135 |
+
: For instruction tuned model variant: natural language text or prompt
|
136 |
+
|
137 |
+
Outputs
|
138 |
+
: For pretrained model variants: fill-in-the-middle code completion, code and natural language
|
139 |
+
: For instruction tuned model variant: code and natural language
|
140 |
+
|
141 |
+
## Model Data
|
142 |
+
|
143 |
+
Data used for model training and how the data was processed.
|
144 |
+
|
145 |
+
### Training Dataset
|
146 |
+
|
147 |
+
Using Gemma as the base model, CodeGemma 2B and 7B pretrained variants are further trained on an additional 500 billion tokens of primarily English language data from publicly available code repositories, open source mathematics datasets and synthetically generated code.
|
148 |
+
|
149 |
+
### Training Data Processing
|
150 |
+
|
151 |
+
The following data pre-processing techniques were applied:
|
152 |
+
|
153 |
+
* FIM Pretrained CodeGemma models focus on fill-in-the-middle (FIM) tasks. The models are trained to work with both PSM and SPM modes. Our FIM settings are 80% FIM rate with 50-50 PSM/SPM.
|
154 |
+
* Dependency Graph-based Packing and Unit Test-based Lexical Packing techniques: To improve model alignment with real-world applications, we structured training examples at the project/repository level to co-locate the most relevant source files within each repository. Specifically, we employed two heuristic techniques: dependency graph-based packing and unit test-based lexical packing
|
155 |
+
* We developed a novel technique for splitting the documents into prefix, middle, and suffix to make the suffix start in a more syntactically natural point rather than purely random distribution.
|
156 |
+
* Safety: Similarly to Gemma, we deployed rigorous safety filtering including filtering personal data, CSAM filtering and other filtering based on content quality and safety in line with [our policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11).
|
157 |
+
|
158 |
+
## Implementation Information
|
159 |
+
|
160 |
+
Information about the hardware and software used to train the models.
|
161 |
+
|
162 |
+
### Hardware
|
163 |
+
|
164 |
+
CodeGemma was trained using the latest generation of [Tensor Processing Unit (TPU)](https://cloud.google.com/tpu/docs/intro-to-tpu) hardware (TPUv5e).
|
165 |
+
|
166 |
+
### Software
|
167 |
+
|
168 |
+
Training was done using [JAX](https://github.com/google/jax) and [ML Pathways](https://blog.google/technology/ai/introducing-pathways-next-generation-ai-architecture/).
|
169 |
+
|
170 |
+
## Evaluation Information
|
171 |
+
|
172 |
+
Model evaluation metrics and results.
|
173 |
+
|
174 |
+
### Evaluation Approach
|
175 |
+
|
176 |
+
We evaluate CodeGemma on a variety of academic benchmarks across several domains:
|
177 |
+
|
178 |
+
* Code completion benchmarks: HumanEval Single Line and Multiple Line Infilling
|
179 |
+
* Code generation benchmarks: HumanEval, MBPP, BabelCode (C++, C#, Go, Java, JavaScript, Kotlin, Python, Rust)
|
180 |
+
* Q&A: BoolQ, PIQA, TriviaQA
|
181 |
+
* Natural Language: ARC-Challenge, HellaSwag, MMLU, WinoGrande
|
182 |
+
* Math Reasoning: GSM8K, MATH
|
183 |
+
|
184 |
+
### Evaluation Results
|
185 |
+
|
186 |
+
#### Coding Benchmarks
|
187 |
+
|
188 |
+
Benchmark | 2B | 7B | 7B-IT
|
189 |
+
----------------------|-------|-------|------
|
190 |
+
HumanEval | 31.1 | 44.5 | 56.1
|
191 |
+
MBPP | 43.6 | 56.2 | 54.2
|
192 |
+
HumanEval Single Line | 78.41 | 76.09 | 68.25
|
193 |
+
HumanEval Multi Line | 51.44 | 58.44 | 20.05
|
194 |
+
BC HE C++ | 24.2 | 32.9 | 42.2
|
195 |
+
BC HE C# | 10.6 | 22.4 | 26.7
|
196 |
+
BC HE Go | 20.5 | 21.7 | 28.6
|
197 |
+
BC HE Java | 29.2 | 41.0 | 48.4
|
198 |
+
BC HE JavaScript | 21.7 | 39.8 | 46.0
|
199 |
+
BC HE Kotlin | 28.0 | 39.8 | 51.6
|
200 |
+
BC HE Python | 21.7 | 42.2 | 48.4
|
201 |
+
BC HE Rust | 26.7 | 34.1 | 36.0
|
202 |
+
BC MBPP C++ | 47.1 | 53.8 | 56.7
|
203 |
+
BC MBPP C# | 28.7 | 32.5 | 41.2
|
204 |
+
BC MBPP Go | 45.6 | 43.3 | 46.2
|
205 |
+
BC MBPP Java | 41.8 | 50.3 | 57.3
|
206 |
+
BC MBPP JavaScript | 45.3 | 58.2 | 61.4
|
207 |
+
BC MBPP Kotlin | 46.8 | 54.7 | 59.9
|
208 |
+
BC MBPP Python | 38.6 | 59.1 | 62.0
|
209 |
+
BC MBPP Rust | 45.3 | 52.9 | 53.5
|
210 |
+
|
211 |
+
#### Natural Language Benchmarks
|
212 |
+
|
213 |
+
![CodeGemma Natural Language Benchmarks](./codegemma_nl_benchmarks.png)
|
214 |
+
|
215 |
+
## Ethics and Safety
|
216 |
+
|
217 |
+
Ethics and safety evaluation approach and results.
|
218 |
+
|
219 |
+
### Evaluation Approach
|
220 |
+
|
221 |
+
Our evaluation methods include structured evaluations and internal red-teaming testing of relevant content policies. Red-teaming was conducted by a number of different teams, each with different goals and human evaluation metrics. These models were evaluated against a number of different categories relevant to ethics and safety, including:
|
222 |
+
|
223 |
+
* Human evaluation on prompts covering content safety and representational harms. See the [Gemma model card](https://ai.google.dev/gemma/docs/model_card#evaluation_approach) for more details on evaluation approach.
|
224 |
+
* Specific testing of cyber-offence capabilities, focusing on testing autonomous hacking capabilities and ensuring potential harms are limited.
|
225 |
+
|
226 |
+
### Evaluation Results
|
227 |
+
|
228 |
+
The results of ethics and safety evaluations are within acceptable thresholds for meeting [internal policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11) for categories such as child safety, content safety, representational harms, memorization, large-scale harms. See the [Gemma model card](https://ai.google.dev/gemma/docs/model_card#evaluation_results) for more details.
|
229 |
+
|
230 |
+
## Model Usage & Limitations
|
231 |
+
|
232 |
+
These models have certain limitations that users should be aware of.
|
233 |
+
|
234 |
+
### Intended Usage
|
235 |
+
|
236 |
+
Code Gemma models have a wide range of applications, which vary between IT and PT models. The following list of potential uses is not comprehensive. The purpose of this list is to provide contextual information about the possible use-cases that the model creators considered as part of model training and development.
|
237 |
+
|
238 |
+
Code Completion
|
239 |
+
: PT models can be used to complete code with an IDE extension
|
240 |
+
|
241 |
+
Code Generation
|
242 |
+
: IT model can be used to generate code with or without an IDE extension
|
243 |
+
|
244 |
+
Code Conversation
|
245 |
+
: IT model can power conversation interfaces which discuss code.
|
246 |
+
|
247 |
+
Code Education
|
248 |
+
: IT model supports interactive code learning experiences, aids in syntax correction or provides coding practice.
|
249 |
+
|
250 |
+
### Known Limitations
|
251 |
+
|
252 |
+
Large Language Models (LLMs) have limitations based on their training data and the inherent limitations of the technology. See the [Gemma model card](https://ai.google.dev/gemma/docs/model_card#evaluation_results) for more details on the limitations of LLMs.
|
253 |
+
|
254 |
+
### Ethical Considerations & Risks
|
255 |
+
|
256 |
+
The development of large language models (LLMs) raises several ethical concerns. We have carefully considered multiple aspects in the development of these models. Please refer to [the same discussion](https://ai.google.dev/gemma/docs/model_card#ethical_considerations_and_risks) in the Gemma model card for model details.
|
257 |
+
|
258 |
+
### Benefits
|
259 |
+
|
260 |
+
At the time of release, this family of models provides high-performance open code-focused large language model implementations designed from the ground up for Responsible AI development compared to similarly sized models.
|
261 |
+
|
262 |
+
Using the coding benchmark evaluation metrics described in this document, these models have shown to provide superior performance to other, comparably-sized open model alternatives.
|
APA/0/gemma/code_gemma__7b/codegemma_nl_benchmarks.png
ADDED
![]() |
APA/0/gemma/code_gemma__7b/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"GemmaForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 2,
|
8 |
+
"eos_token_id": 1,
|
9 |
+
"head_dim": 256,
|
10 |
+
"hidden_activation": "gelu_pytorch_tanh",
|
11 |
+
"hidden_size": 3072,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 24576,
|
14 |
+
"max_position_embeddings": 8192,
|
15 |
+
"model_type": "gemma",
|
16 |
+
"num_attention_heads": 16,
|
17 |
+
"num_hidden_layers": 28,
|
18 |
+
"num_key_value_heads": 16,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"rms_norm_eps": 1e-06,
|
21 |
+
"rope_theta": 10000.0,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.39.3",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 256000
|
26 |
+
}
|
APA/0/gemma/code_gemma__7b/generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 2,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.39.3"
|
7 |
+
}
|
APA/0/gemma/code_gemma__7b/model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9167cf03780d5d7e0682826d51fe3cd03ccb2449b27aa40c90ca4b64f0901aee
|
3 |
+
size 4995496656
|
APA/0/gemma/code_gemma__7b/model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da22f51c0d055ffc4b7d6ef4cb1509df6c8f9f0c6ea14be0ad8a729ba8193f15
|
3 |
+
size 4982953168
|
APA/0/gemma/code_gemma__7b/model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43845ddfcb04afa9d6b1f72a3b4ff6272ab8b1a3cb2fa473fc42cfb433a96a8d
|
3 |
+
size 4982953200
|
APA/0/gemma/code_gemma__7b/model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8a4286add77b8a3d86fa5eab4da890e8eca27e99637be07909afe34d81d46d25
|
3 |
+
size 2113988336
|
APA/0/gemma/code_gemma__7b/model.safetensors.index.json
ADDED
@@ -0,0 +1,261 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 17075361792
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
7 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
8 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
9 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
10 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
11 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
12 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
13 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
14 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
15 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
16 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
17 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
18 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
19 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
20 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
21 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
22 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
23 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
24 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
25 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
26 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
27 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
28 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
29 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
30 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
31 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
32 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
33 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
34 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
35 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
36 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
37 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
38 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
39 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
40 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
41 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
42 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
43 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
44 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
45 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
46 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
47 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
48 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
49 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
50 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
51 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
52 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
53 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
54 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
55 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
56 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
57 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
58 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
59 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
60 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
61 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
62 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
63 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
64 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
65 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
66 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
67 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
68 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
69 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
70 |
+
"model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
71 |
+
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
72 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
73 |
+
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
74 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
75 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
76 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
77 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
78 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
79 |
+
"model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
80 |
+
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
81 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
82 |
+
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
83 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
84 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
85 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
86 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
87 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
88 |
+
"model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
89 |
+
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
90 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
91 |
+
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
92 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
93 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
94 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
95 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
96 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
97 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
98 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
99 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
100 |
+
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
101 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
102 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
103 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
104 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
105 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
106 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
107 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
108 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
109 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
110 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
111 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
112 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
113 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
114 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
115 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
116 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
117 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
118 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
119 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
120 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
121 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
122 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
123 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
124 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
125 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
126 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
127 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
128 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
129 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
130 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
131 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
132 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
133 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
134 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
135 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
136 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
137 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
138 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
139 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
140 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
141 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
142 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
143 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
144 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
145 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
146 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
147 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
148 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
149 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
150 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
151 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
152 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
153 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
154 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
155 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
156 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
157 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
158 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
159 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
160 |
+
"model.layers.24.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
161 |
+
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
162 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
163 |
+
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
164 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
165 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
166 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
167 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
168 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
169 |
+
"model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
170 |
+
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
171 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
172 |
+
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
173 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
174 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
175 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
176 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
177 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
178 |
+
"model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
179 |
+
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
180 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
181 |
+
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
182 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
183 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
184 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
185 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
186 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
187 |
+
"model.layers.27.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
188 |
+
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
189 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
190 |
+
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
191 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
192 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
193 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
194 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
195 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
196 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
197 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
198 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
199 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
200 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
201 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
202 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
203 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
204 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
205 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
206 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
207 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
208 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
209 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
210 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
211 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
212 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
213 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
214 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
215 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
216 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
217 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
218 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
219 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
220 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
221 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
222 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
223 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
224 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
225 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
226 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
227 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
228 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
229 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
230 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
231 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
232 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
233 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
234 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
235 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
236 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
237 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
238 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
239 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
240 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
241 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
242 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
243 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
244 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
245 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
246 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
247 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
248 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
249 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
250 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
251 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
252 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
253 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
254 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
255 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
256 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
257 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
258 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
259 |
+
"model.norm.weight": "model-00004-of-00004.safetensors"
|
260 |
+
}
|
261 |
+
}
|
APA/0/gemma/code_gemma__7b/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<bos>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<eos>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<pad>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
APA/0/gemma/code_gemma__7b/tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7ebb96114e033c4ee00b6991644672cf1f9d1d27e60381ee66caf466fe62339
|
3 |
+
size 17518540
|
APA/0/gemma/code_gemma__7b/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:583f2ebd2a1936009b7da991ea255504db68c7a9713a78673d1335a87098966c
|
3 |
+
size 4241023
|
APA/0/gemma/code_gemma__7b/tokenizer_config.json
ADDED
@@ -0,0 +1,1512 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<pad>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<eos>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<bos>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"3": {
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"4": {
|
38 |
+
"content": "<mask>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": false
|
44 |
+
},
|
45 |
+
"5": {
|
46 |
+
"content": "<2mass>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": false
|
52 |
+
},
|
53 |
+
"6": {
|
54 |
+
"content": "[@BOS@]",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": false
|
60 |
+
},
|
61 |
+
"7": {
|
62 |
+
"content": "<unused0>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": false
|
68 |
+
},
|
69 |
+
"8": {
|
70 |
+
"content": "<unused1>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": false
|
76 |
+
},
|
77 |
+
"9": {
|
78 |
+
"content": "<unused2>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": false
|
84 |
+
},
|
85 |
+
"10": {
|
86 |
+
"content": "<unused3>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": false
|
92 |
+
},
|
93 |
+
"11": {
|
94 |
+
"content": "<unused4>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": false
|
100 |
+
},
|
101 |
+
"12": {
|
102 |
+
"content": "<unused5>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": false
|
108 |
+
},
|
109 |
+
"13": {
|
110 |
+
"content": "<unused6>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": false
|
116 |
+
},
|
117 |
+
"14": {
|
118 |
+
"content": "<unused7>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"15": {
|
126 |
+
"content": "<unused8>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"16": {
|
134 |
+
"content": "<unused9>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"17": {
|
142 |
+
"content": "<unused10>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"18": {
|
150 |
+
"content": "<unused11>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"19": {
|
158 |
+
"content": "<unused12>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"20": {
|
166 |
+
"content": "<unused13>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"21": {
|
174 |
+
"content": "<unused14>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
},
|
181 |
+
"22": {
|
182 |
+
"content": "<unused15>",
|
183 |
+
"lstrip": false,
|
184 |
+
"normalized": false,
|
185 |
+
"rstrip": false,
|
186 |
+
"single_word": false,
|
187 |
+
"special": false
|
188 |
+
},
|
189 |
+
"23": {
|
190 |
+
"content": "<unused16>",
|
191 |
+
"lstrip": false,
|
192 |
+
"normalized": false,
|
193 |
+
"rstrip": false,
|
194 |
+
"single_word": false,
|
195 |
+
"special": false
|
196 |
+
},
|
197 |
+
"24": {
|
198 |
+
"content": "<unused17>",
|
199 |
+
"lstrip": false,
|
200 |
+
"normalized": false,
|
201 |
+
"rstrip": false,
|
202 |
+
"single_word": false,
|
203 |
+
"special": false
|
204 |
+
},
|
205 |
+
"25": {
|
206 |
+
"content": "<unused18>",
|
207 |
+
"lstrip": false,
|
208 |
+
"normalized": false,
|
209 |
+
"rstrip": false,
|
210 |
+
"single_word": false,
|
211 |
+
"special": false
|
212 |
+
},
|
213 |
+
"26": {
|
214 |
+
"content": "<unused19>",
|
215 |
+
"lstrip": false,
|
216 |
+
"normalized": false,
|
217 |
+
"rstrip": false,
|
218 |
+
"single_word": false,
|
219 |
+
"special": false
|
220 |
+
},
|
221 |
+
"27": {
|
222 |
+
"content": "<unused20>",
|
223 |
+
"lstrip": false,
|
224 |
+
"normalized": false,
|
225 |
+
"rstrip": false,
|
226 |
+
"single_word": false,
|
227 |
+
"special": false
|
228 |
+
},
|
229 |
+
"28": {
|
230 |
+
"content": "<unused21>",
|
231 |
+
"lstrip": false,
|
232 |
+
"normalized": false,
|
233 |
+
"rstrip": false,
|
234 |
+
"single_word": false,
|
235 |
+
"special": false
|
236 |
+
},
|
237 |
+
"29": {
|
238 |
+
"content": "<unused22>",
|
239 |
+
"lstrip": false,
|
240 |
+
"normalized": false,
|
241 |
+
"rstrip": false,
|
242 |
+
"single_word": false,
|
243 |
+
"special": false
|
244 |
+
},
|
245 |
+
"30": {
|
246 |
+
"content": "<unused23>",
|
247 |
+
"lstrip": false,
|
248 |
+
"normalized": false,
|
249 |
+
"rstrip": false,
|
250 |
+
"single_word": false,
|
251 |
+
"special": false
|
252 |
+
},
|
253 |
+
"31": {
|
254 |
+
"content": "<unused24>",
|
255 |
+
"lstrip": false,
|
256 |
+
"normalized": false,
|
257 |
+
"rstrip": false,
|
258 |
+
"single_word": false,
|
259 |
+
"special": false
|
260 |
+
},
|
261 |
+
"32": {
|
262 |
+
"content": "<unused25>",
|
263 |
+
"lstrip": false,
|
264 |
+
"normalized": false,
|
265 |
+
"rstrip": false,
|
266 |
+
"single_word": false,
|
267 |
+
"special": false
|
268 |
+
},
|
269 |
+
"33": {
|
270 |
+
"content": "<unused26>",
|
271 |
+
"lstrip": false,
|
272 |
+
"normalized": false,
|
273 |
+
"rstrip": false,
|
274 |
+
"single_word": false,
|
275 |
+
"special": false
|
276 |
+
},
|
277 |
+
"34": {
|
278 |
+
"content": "<unused27>",
|
279 |
+
"lstrip": false,
|
280 |
+
"normalized": false,
|
281 |
+
"rstrip": false,
|
282 |
+
"single_word": false,
|
283 |
+
"special": false
|
284 |
+
},
|
285 |
+
"35": {
|
286 |
+
"content": "<unused28>",
|
287 |
+
"lstrip": false,
|
288 |
+
"normalized": false,
|
289 |
+
"rstrip": false,
|
290 |
+
"single_word": false,
|
291 |
+
"special": false
|
292 |
+
},
|
293 |
+
"36": {
|
294 |
+
"content": "<unused29>",
|
295 |
+
"lstrip": false,
|
296 |
+
"normalized": false,
|
297 |
+
"rstrip": false,
|
298 |
+
"single_word": false,
|
299 |
+
"special": false
|
300 |
+
},
|
301 |
+
"37": {
|
302 |
+
"content": "<unused30>",
|
303 |
+
"lstrip": false,
|
304 |
+
"normalized": false,
|
305 |
+
"rstrip": false,
|
306 |
+
"single_word": false,
|
307 |
+
"special": false
|
308 |
+
},
|
309 |
+
"38": {
|
310 |
+
"content": "<unused31>",
|
311 |
+
"lstrip": false,
|
312 |
+
"normalized": false,
|
313 |
+
"rstrip": false,
|
314 |
+
"single_word": false,
|
315 |
+
"special": false
|
316 |
+
},
|
317 |
+
"39": {
|
318 |
+
"content": "<unused32>",
|
319 |
+
"lstrip": false,
|
320 |
+
"normalized": false,
|
321 |
+
"rstrip": false,
|
322 |
+
"single_word": false,
|
323 |
+
"special": false
|
324 |
+
},
|
325 |
+
"40": {
|
326 |
+
"content": "<unused33>",
|
327 |
+
"lstrip": false,
|
328 |
+
"normalized": false,
|
329 |
+
"rstrip": false,
|
330 |
+
"single_word": false,
|
331 |
+
"special": false
|
332 |
+
},
|
333 |
+
"41": {
|
334 |
+
"content": "<unused34>",
|
335 |
+
"lstrip": false,
|
336 |
+
"normalized": false,
|
337 |
+
"rstrip": false,
|
338 |
+
"single_word": false,
|
339 |
+
"special": false
|
340 |
+
},
|
341 |
+
"42": {
|
342 |
+
"content": "<unused35>",
|
343 |
+
"lstrip": false,
|
344 |
+
"normalized": false,
|
345 |
+
"rstrip": false,
|
346 |
+
"single_word": false,
|
347 |
+
"special": false
|
348 |
+
},
|
349 |
+
"43": {
|
350 |
+
"content": "<unused36>",
|
351 |
+
"lstrip": false,
|
352 |
+
"normalized": false,
|
353 |
+
"rstrip": false,
|
354 |
+
"single_word": false,
|
355 |
+
"special": false
|
356 |
+
},
|
357 |
+
"44": {
|
358 |
+
"content": "<unused37>",
|
359 |
+
"lstrip": false,
|
360 |
+
"normalized": false,
|
361 |
+
"rstrip": false,
|
362 |
+
"single_word": false,
|
363 |
+
"special": false
|
364 |
+
},
|
365 |
+
"45": {
|
366 |
+
"content": "<unused38>",
|
367 |
+
"lstrip": false,
|
368 |
+
"normalized": false,
|
369 |
+
"rstrip": false,
|
370 |
+
"single_word": false,
|
371 |
+
"special": false
|
372 |
+
},
|
373 |
+
"46": {
|
374 |
+
"content": "<unused39>",
|
375 |
+
"lstrip": false,
|
376 |
+
"normalized": false,
|
377 |
+
"rstrip": false,
|
378 |
+
"single_word": false,
|
379 |
+
"special": false
|
380 |
+
},
|
381 |
+
"47": {
|
382 |
+
"content": "<unused40>",
|
383 |
+
"lstrip": false,
|
384 |
+
"normalized": false,
|
385 |
+
"rstrip": false,
|
386 |
+
"single_word": false,
|
387 |
+
"special": false
|
388 |
+
},
|
389 |
+
"48": {
|
390 |
+
"content": "<unused41>",
|
391 |
+
"lstrip": false,
|
392 |
+
"normalized": false,
|
393 |
+
"rstrip": false,
|
394 |
+
"single_word": false,
|
395 |
+
"special": false
|
396 |
+
},
|
397 |
+
"49": {
|
398 |
+
"content": "<unused42>",
|
399 |
+
"lstrip": false,
|
400 |
+
"normalized": false,
|
401 |
+
"rstrip": false,
|
402 |
+
"single_word": false,
|
403 |
+
"special": false
|
404 |
+
},
|
405 |
+
"50": {
|
406 |
+
"content": "<unused43>",
|
407 |
+
"lstrip": false,
|
408 |
+
"normalized": false,
|
409 |
+
"rstrip": false,
|
410 |
+
"single_word": false,
|
411 |
+
"special": false
|
412 |
+
},
|
413 |
+
"51": {
|
414 |
+
"content": "<unused44>",
|
415 |
+
"lstrip": false,
|
416 |
+
"normalized": false,
|
417 |
+
"rstrip": false,
|
418 |
+
"single_word": false,
|
419 |
+
"special": false
|
420 |
+
},
|
421 |
+
"52": {
|
422 |
+
"content": "<unused45>",
|
423 |
+
"lstrip": false,
|
424 |
+
"normalized": false,
|
425 |
+
"rstrip": false,
|
426 |
+
"single_word": false,
|
427 |
+
"special": false
|
428 |
+
},
|
429 |
+
"53": {
|
430 |
+
"content": "<unused46>",
|
431 |
+
"lstrip": false,
|
432 |
+
"normalized": false,
|
433 |
+
"rstrip": false,
|
434 |
+
"single_word": false,
|
435 |
+
"special": false
|
436 |
+
},
|
437 |
+
"54": {
|
438 |
+
"content": "<unused47>",
|
439 |
+
"lstrip": false,
|
440 |
+
"normalized": false,
|
441 |
+
"rstrip": false,
|
442 |
+
"single_word": false,
|
443 |
+
"special": false
|
444 |
+
},
|
445 |
+
"55": {
|
446 |
+
"content": "<unused48>",
|
447 |
+
"lstrip": false,
|
448 |
+
"normalized": false,
|
449 |
+
"rstrip": false,
|
450 |
+
"single_word": false,
|
451 |
+
"special": false
|
452 |
+
},
|
453 |
+
"56": {
|
454 |
+
"content": "<unused49>",
|
455 |
+
"lstrip": false,
|
456 |
+
"normalized": false,
|
457 |
+
"rstrip": false,
|
458 |
+
"single_word": false,
|
459 |
+
"special": false
|
460 |
+
},
|
461 |
+
"57": {
|
462 |
+
"content": "<unused50>",
|
463 |
+
"lstrip": false,
|
464 |
+
"normalized": false,
|
465 |
+
"rstrip": false,
|
466 |
+
"single_word": false,
|
467 |
+
"special": false
|
468 |
+
},
|
469 |
+
"58": {
|
470 |
+
"content": "<unused51>",
|
471 |
+
"lstrip": false,
|
472 |
+
"normalized": false,
|
473 |
+
"rstrip": false,
|
474 |
+
"single_word": false,
|
475 |
+
"special": false
|
476 |
+
},
|
477 |
+
"59": {
|
478 |
+
"content": "<unused52>",
|
479 |
+
"lstrip": false,
|
480 |
+
"normalized": false,
|
481 |
+
"rstrip": false,
|
482 |
+
"single_word": false,
|
483 |
+
"special": false
|
484 |
+
},
|
485 |
+
"60": {
|
486 |
+
"content": "<unused53>",
|
487 |
+
"lstrip": false,
|
488 |
+
"normalized": false,
|
489 |
+
"rstrip": false,
|
490 |
+
"single_word": false,
|
491 |
+
"special": false
|
492 |
+
},
|
493 |
+
"61": {
|
494 |
+
"content": "<unused54>",
|
495 |
+
"lstrip": false,
|
496 |
+
"normalized": false,
|
497 |
+
"rstrip": false,
|
498 |
+
"single_word": false,
|
499 |
+
"special": false
|
500 |
+
},
|
501 |
+
"62": {
|
502 |
+
"content": "<unused55>",
|
503 |
+
"lstrip": false,
|
504 |
+
"normalized": false,
|
505 |
+
"rstrip": false,
|
506 |
+
"single_word": false,
|
507 |
+
"special": false
|
508 |
+
},
|
509 |
+
"63": {
|
510 |
+
"content": "<unused56>",
|
511 |
+
"lstrip": false,
|
512 |
+
"normalized": false,
|
513 |
+
"rstrip": false,
|
514 |
+
"single_word": false,
|
515 |
+
"special": false
|
516 |
+
},
|
517 |
+
"64": {
|
518 |
+
"content": "<unused57>",
|
519 |
+
"lstrip": false,
|
520 |
+
"normalized": false,
|
521 |
+
"rstrip": false,
|
522 |
+
"single_word": false,
|
523 |
+
"special": false
|
524 |
+
},
|
525 |
+
"65": {
|
526 |
+
"content": "<unused58>",
|
527 |
+
"lstrip": false,
|
528 |
+
"normalized": false,
|
529 |
+
"rstrip": false,
|
530 |
+
"single_word": false,
|
531 |
+
"special": false
|
532 |
+
},
|
533 |
+
"66": {
|
534 |
+
"content": "<unused59>",
|
535 |
+
"lstrip": false,
|
536 |
+
"normalized": false,
|
537 |
+
"rstrip": false,
|
538 |
+
"single_word": false,
|
539 |
+
"special": false
|
540 |
+
},
|
541 |
+
"67": {
|
542 |
+
"content": "<|fim_prefix|>",
|
543 |
+
"lstrip": false,
|
544 |
+
"normalized": false,
|
545 |
+
"rstrip": false,
|
546 |
+
"single_word": false,
|
547 |
+
"special": false
|
548 |
+
},
|
549 |
+
"68": {
|
550 |
+
"content": "<|fim_middle|>",
|
551 |
+
"lstrip": false,
|
552 |
+
"normalized": false,
|
553 |
+
"rstrip": false,
|
554 |
+
"single_word": false,
|
555 |
+
"special": false
|
556 |
+
},
|
557 |
+
"69": {
|
558 |
+
"content": "<|fim_suffix|>",
|
559 |
+
"lstrip": false,
|
560 |
+
"normalized": false,
|
561 |
+
"rstrip": false,
|
562 |
+
"single_word": false,
|
563 |
+
"special": false
|
564 |
+
},
|
565 |
+
"70": {
|
566 |
+
"content": "<|file_separator|>",
|
567 |
+
"lstrip": false,
|
568 |
+
"normalized": false,
|
569 |
+
"rstrip": false,
|
570 |
+
"single_word": false,
|
571 |
+
"special": false
|
572 |
+
},
|
573 |
+
"71": {
|
574 |
+
"content": "<unused64>",
|
575 |
+
"lstrip": false,
|
576 |
+
"normalized": false,
|
577 |
+
"rstrip": false,
|
578 |
+
"single_word": false,
|
579 |
+
"special": false
|
580 |
+
},
|
581 |
+
"72": {
|
582 |
+
"content": "<unused65>",
|
583 |
+
"lstrip": false,
|
584 |
+
"normalized": false,
|
585 |
+
"rstrip": false,
|
586 |
+
"single_word": false,
|
587 |
+
"special": false
|
588 |
+
},
|
589 |
+
"73": {
|
590 |
+
"content": "<unused66>",
|
591 |
+
"lstrip": false,
|
592 |
+
"normalized": false,
|
593 |
+
"rstrip": false,
|
594 |
+
"single_word": false,
|
595 |
+
"special": false
|
596 |
+
},
|
597 |
+
"74": {
|
598 |
+
"content": "<unused67>",
|
599 |
+
"lstrip": false,
|
600 |
+
"normalized": false,
|
601 |
+
"rstrip": false,
|
602 |
+
"single_word": false,
|
603 |
+
"special": false
|
604 |
+
},
|
605 |
+
"75": {
|
606 |
+
"content": "<unused68>",
|
607 |
+
"lstrip": false,
|
608 |
+
"normalized": false,
|
609 |
+
"rstrip": false,
|
610 |
+
"single_word": false,
|
611 |
+
"special": false
|
612 |
+
},
|
613 |
+
"76": {
|
614 |
+
"content": "<unused69>",
|
615 |
+
"lstrip": false,
|
616 |
+
"normalized": false,
|
617 |
+
"rstrip": false,
|
618 |
+
"single_word": false,
|
619 |
+
"special": false
|
620 |
+
},
|
621 |
+
"77": {
|
622 |
+
"content": "<unused70>",
|
623 |
+
"lstrip": false,
|
624 |
+
"normalized": false,
|
625 |
+
"rstrip": false,
|
626 |
+
"single_word": false,
|
627 |
+
"special": false
|
628 |
+
},
|
629 |
+
"78": {
|
630 |
+
"content": "<unused71>",
|
631 |
+
"lstrip": false,
|
632 |
+
"normalized": false,
|
633 |
+
"rstrip": false,
|
634 |
+
"single_word": false,
|
635 |
+
"special": false
|
636 |
+
},
|
637 |
+
"79": {
|
638 |
+
"content": "<unused72>",
|
639 |
+
"lstrip": false,
|
640 |
+
"normalized": false,
|
641 |
+
"rstrip": false,
|
642 |
+
"single_word": false,
|
643 |
+
"special": false
|
644 |
+
},
|
645 |
+
"80": {
|
646 |
+
"content": "<unused73>",
|
647 |
+
"lstrip": false,
|
648 |
+
"normalized": false,
|
649 |
+
"rstrip": false,
|
650 |
+
"single_word": false,
|
651 |
+
"special": false
|
652 |
+
},
|
653 |
+
"81": {
|
654 |
+
"content": "<unused74>",
|
655 |
+
"lstrip": false,
|
656 |
+
"normalized": false,
|
657 |
+
"rstrip": false,
|
658 |
+
"single_word": false,
|
659 |
+
"special": false
|
660 |
+
},
|
661 |
+
"82": {
|
662 |
+
"content": "<unused75>",
|
663 |
+
"lstrip": false,
|
664 |
+
"normalized": false,
|
665 |
+
"rstrip": false,
|
666 |
+
"single_word": false,
|
667 |
+
"special": false
|
668 |
+
},
|
669 |
+
"83": {
|
670 |
+
"content": "<unused76>",
|
671 |
+
"lstrip": false,
|
672 |
+
"normalized": false,
|
673 |
+
"rstrip": false,
|
674 |
+
"single_word": false,
|
675 |
+
"special": false
|
676 |
+
},
|
677 |
+
"84": {
|
678 |
+
"content": "<unused77>",
|
679 |
+
"lstrip": false,
|
680 |
+
"normalized": false,
|
681 |
+
"rstrip": false,
|
682 |
+
"single_word": false,
|
683 |
+
"special": false
|
684 |
+
},
|
685 |
+
"85": {
|
686 |
+
"content": "<unused78>",
|
687 |
+
"lstrip": false,
|
688 |
+
"normalized": false,
|
689 |
+
"rstrip": false,
|
690 |
+
"single_word": false,
|
691 |
+
"special": false
|
692 |
+
},
|
693 |
+
"86": {
|
694 |
+
"content": "<unused79>",
|
695 |
+
"lstrip": false,
|
696 |
+
"normalized": false,
|
697 |
+
"rstrip": false,
|
698 |
+
"single_word": false,
|
699 |
+
"special": false
|
700 |
+
},
|
701 |
+
"87": {
|
702 |
+
"content": "<unused80>",
|
703 |
+
"lstrip": false,
|
704 |
+
"normalized": false,
|
705 |
+
"rstrip": false,
|
706 |
+
"single_word": false,
|
707 |
+
"special": false
|
708 |
+
},
|
709 |
+
"88": {
|
710 |
+
"content": "<unused81>",
|
711 |
+
"lstrip": false,
|
712 |
+
"normalized": false,
|
713 |
+
"rstrip": false,
|
714 |
+
"single_word": false,
|
715 |
+
"special": false
|
716 |
+
},
|
717 |
+
"89": {
|
718 |
+
"content": "<unused82>",
|
719 |
+
"lstrip": false,
|
720 |
+
"normalized": false,
|
721 |
+
"rstrip": false,
|
722 |
+
"single_word": false,
|
723 |
+
"special": false
|
724 |
+
},
|
725 |
+
"90": {
|
726 |
+
"content": "<unused83>",
|
727 |
+
"lstrip": false,
|
728 |
+
"normalized": false,
|
729 |
+
"rstrip": false,
|
730 |
+
"single_word": false,
|
731 |
+
"special": false
|
732 |
+
},
|
733 |
+
"91": {
|
734 |
+
"content": "<unused84>",
|
735 |
+
"lstrip": false,
|
736 |
+
"normalized": false,
|
737 |
+
"rstrip": false,
|
738 |
+
"single_word": false,
|
739 |
+
"special": false
|
740 |
+
},
|
741 |
+
"92": {
|
742 |
+
"content": "<unused85>",
|
743 |
+
"lstrip": false,
|
744 |
+
"normalized": false,
|
745 |
+
"rstrip": false,
|
746 |
+
"single_word": false,
|
747 |
+
"special": false
|
748 |
+
},
|
749 |
+
"93": {
|
750 |
+
"content": "<unused86>",
|
751 |
+
"lstrip": false,
|
752 |
+
"normalized": false,
|
753 |
+
"rstrip": false,
|
754 |
+
"single_word": false,
|
755 |
+
"special": false
|
756 |
+
},
|
757 |
+
"94": {
|
758 |
+
"content": "<unused87>",
|
759 |
+
"lstrip": false,
|
760 |
+
"normalized": false,
|
761 |
+
"rstrip": false,
|
762 |
+
"single_word": false,
|
763 |
+
"special": false
|
764 |
+
},
|
765 |
+
"95": {
|
766 |
+
"content": "<unused88>",
|
767 |
+
"lstrip": false,
|
768 |
+
"normalized": false,
|
769 |
+
"rstrip": false,
|
770 |
+
"single_word": false,
|
771 |
+
"special": false
|
772 |
+
},
|
773 |
+
"96": {
|
774 |
+
"content": "<unused89>",
|
775 |
+
"lstrip": false,
|
776 |
+
"normalized": false,
|
777 |
+
"rstrip": false,
|
778 |
+
"single_word": false,
|
779 |
+
"special": false
|
780 |
+
},
|
781 |
+
"97": {
|
782 |
+
"content": "<unused90>",
|
783 |
+
"lstrip": false,
|
784 |
+
"normalized": false,
|
785 |
+
"rstrip": false,
|
786 |
+
"single_word": false,
|
787 |
+
"special": false
|
788 |
+
},
|
789 |
+
"98": {
|
790 |
+
"content": "<unused91>",
|
791 |
+
"lstrip": false,
|
792 |
+
"normalized": false,
|
793 |
+
"rstrip": false,
|
794 |
+
"single_word": false,
|
795 |
+
"special": false
|
796 |
+
},
|
797 |
+
"99": {
|
798 |
+
"content": "<unused92>",
|
799 |
+
"lstrip": false,
|
800 |
+
"normalized": false,
|
801 |
+
"rstrip": false,
|
802 |
+
"single_word": false,
|
803 |
+
"special": false
|
804 |
+
},
|
805 |
+
"100": {
|
806 |
+
"content": "<unused93>",
|
807 |
+
"lstrip": false,
|
808 |
+
"normalized": false,
|
809 |
+
"rstrip": false,
|
810 |
+
"single_word": false,
|
811 |
+
"special": false
|
812 |
+
},
|
813 |
+
"101": {
|
814 |
+
"content": "<unused94>",
|
815 |
+
"lstrip": false,
|
816 |
+
"normalized": false,
|
817 |
+
"rstrip": false,
|
818 |
+
"single_word": false,
|
819 |
+
"special": false
|
820 |
+
},
|
821 |
+
"102": {
|
822 |
+
"content": "<unused95>",
|
823 |
+
"lstrip": false,
|
824 |
+
"normalized": false,
|
825 |
+
"rstrip": false,
|
826 |
+
"single_word": false,
|
827 |
+
"special": false
|
828 |
+
},
|
829 |
+
"103": {
|
830 |
+
"content": "<unused96>",
|
831 |
+
"lstrip": false,
|
832 |
+
"normalized": false,
|
833 |
+
"rstrip": false,
|
834 |
+
"single_word": false,
|
835 |
+
"special": false
|
836 |
+
},
|
837 |
+
"104": {
|
838 |
+
"content": "<unused97>",
|
839 |
+
"lstrip": false,
|
840 |
+
"normalized": false,
|
841 |
+
"rstrip": false,
|
842 |
+
"single_word": false,
|
843 |
+
"special": false
|
844 |
+
},
|
845 |
+
"105": {
|
846 |
+
"content": "<unused98>",
|
847 |
+
"lstrip": false,
|
848 |
+
"normalized": false,
|
849 |
+
"rstrip": false,
|
850 |
+
"single_word": false,
|
851 |
+
"special": false
|
852 |
+
},
|
853 |
+
"106": {
|
854 |
+
"content": "<start_of_turn>",
|
855 |
+
"lstrip": false,
|
856 |
+
"normalized": false,
|
857 |
+
"rstrip": false,
|
858 |
+
"single_word": false,
|
859 |
+
"special": false
|
860 |
+
},
|
861 |
+
"107": {
|
862 |
+
"content": "<end_of_turn>",
|
863 |
+
"lstrip": false,
|
864 |
+
"normalized": false,
|
865 |
+
"rstrip": false,
|
866 |
+
"single_word": false,
|
867 |
+
"special": false
|
868 |
+
},
|
869 |
+
"108": {
|
870 |
+
"content": "\n",
|
871 |
+
"lstrip": false,
|
872 |
+
"normalized": false,
|
873 |
+
"rstrip": false,
|
874 |
+
"single_word": false,
|
875 |
+
"special": false
|
876 |
+
},
|
877 |
+
"109": {
|
878 |
+
"content": "\n\n",
|
879 |
+
"lstrip": false,
|
880 |
+
"normalized": false,
|
881 |
+
"rstrip": false,
|
882 |
+
"single_word": false,
|
883 |
+
"special": false
|
884 |
+
},
|
885 |
+
"110": {
|
886 |
+
"content": "\n\n\n",
|
887 |
+
"lstrip": false,
|
888 |
+
"normalized": false,
|
889 |
+
"rstrip": false,
|
890 |
+
"single_word": false,
|
891 |
+
"special": false
|
892 |
+
},
|
893 |
+
"111": {
|
894 |
+
"content": "\n\n\n\n",
|
895 |
+
"lstrip": false,
|
896 |
+
"normalized": false,
|
897 |
+
"rstrip": false,
|
898 |
+
"single_word": false,
|
899 |
+
"special": false
|
900 |
+
},
|
901 |
+
"112": {
|
902 |
+
"content": "\n\n\n\n\n",
|
903 |
+
"lstrip": false,
|
904 |
+
"normalized": false,
|
905 |
+
"rstrip": false,
|
906 |
+
"single_word": false,
|
907 |
+
"special": false
|
908 |
+
},
|
909 |
+
"113": {
|
910 |
+
"content": "\n\n\n\n\n\n",
|
911 |
+
"lstrip": false,
|
912 |
+
"normalized": false,
|
913 |
+
"rstrip": false,
|
914 |
+
"single_word": false,
|
915 |
+
"special": false
|
916 |
+
},
|
917 |
+
"114": {
|
918 |
+
"content": "\n\n\n\n\n\n\n",
|
919 |
+
"lstrip": false,
|
920 |
+
"normalized": false,
|
921 |
+
"rstrip": false,
|
922 |
+
"single_word": false,
|
923 |
+
"special": false
|
924 |
+
},
|
925 |
+
"115": {
|
926 |
+
"content": "\n\n\n\n\n\n\n\n",
|
927 |
+
"lstrip": false,
|
928 |
+
"normalized": false,
|
929 |
+
"rstrip": false,
|
930 |
+
"single_word": false,
|
931 |
+
"special": false
|
932 |
+
},
|
933 |
+
"116": {
|
934 |
+
"content": "\n\n\n\n\n\n\n\n\n",
|
935 |
+
"lstrip": false,
|
936 |
+
"normalized": false,
|
937 |
+
"rstrip": false,
|
938 |
+
"single_word": false,
|
939 |
+
"special": false
|
940 |
+
},
|
941 |
+
"117": {
|
942 |
+
"content": "\n\n\n\n\n\n\n\n\n\n",
|
943 |
+
"lstrip": false,
|
944 |
+
"normalized": false,
|
945 |
+
"rstrip": false,
|
946 |
+
"single_word": false,
|
947 |
+
"special": false
|
948 |
+
},
|
949 |
+
"118": {
|
950 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n",
|
951 |
+
"lstrip": false,
|
952 |
+
"normalized": false,
|
953 |
+
"rstrip": false,
|
954 |
+
"single_word": false,
|
955 |
+
"special": false
|
956 |
+
},
|
957 |
+
"119": {
|
958 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n",
|
959 |
+
"lstrip": false,
|
960 |
+
"normalized": false,
|
961 |
+
"rstrip": false,
|
962 |
+
"single_word": false,
|
963 |
+
"special": false
|
964 |
+
},
|
965 |
+
"120": {
|
966 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
967 |
+
"lstrip": false,
|
968 |
+
"normalized": false,
|
969 |
+
"rstrip": false,
|
970 |
+
"single_word": false,
|
971 |
+
"special": false
|
972 |
+
},
|
973 |
+
"121": {
|
974 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
975 |
+
"lstrip": false,
|
976 |
+
"normalized": false,
|
977 |
+
"rstrip": false,
|
978 |
+
"single_word": false,
|
979 |
+
"special": false
|
980 |
+
},
|
981 |
+
"122": {
|
982 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
983 |
+
"lstrip": false,
|
984 |
+
"normalized": false,
|
985 |
+
"rstrip": false,
|
986 |
+
"single_word": false,
|
987 |
+
"special": false
|
988 |
+
},
|
989 |
+
"123": {
|
990 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
991 |
+
"lstrip": false,
|
992 |
+
"normalized": false,
|
993 |
+
"rstrip": false,
|
994 |
+
"single_word": false,
|
995 |
+
"special": false
|
996 |
+
},
|
997 |
+
"124": {
|
998 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
999 |
+
"lstrip": false,
|
1000 |
+
"normalized": false,
|
1001 |
+
"rstrip": false,
|
1002 |
+
"single_word": false,
|
1003 |
+
"special": false
|
1004 |
+
},
|
1005 |
+
"125": {
|
1006 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1007 |
+
"lstrip": false,
|
1008 |
+
"normalized": false,
|
1009 |
+
"rstrip": false,
|
1010 |
+
"single_word": false,
|
1011 |
+
"special": false
|
1012 |
+
},
|
1013 |
+
"126": {
|
1014 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1015 |
+
"lstrip": false,
|
1016 |
+
"normalized": false,
|
1017 |
+
"rstrip": false,
|
1018 |
+
"single_word": false,
|
1019 |
+
"special": false
|
1020 |
+
},
|
1021 |
+
"127": {
|
1022 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1023 |
+
"lstrip": false,
|
1024 |
+
"normalized": false,
|
1025 |
+
"rstrip": false,
|
1026 |
+
"single_word": false,
|
1027 |
+
"special": false
|
1028 |
+
},
|
1029 |
+
"128": {
|
1030 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1031 |
+
"lstrip": false,
|
1032 |
+
"normalized": false,
|
1033 |
+
"rstrip": false,
|
1034 |
+
"single_word": false,
|
1035 |
+
"special": false
|
1036 |
+
},
|
1037 |
+
"129": {
|
1038 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1039 |
+
"lstrip": false,
|
1040 |
+
"normalized": false,
|
1041 |
+
"rstrip": false,
|
1042 |
+
"single_word": false,
|
1043 |
+
"special": false
|
1044 |
+
},
|
1045 |
+
"130": {
|
1046 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1047 |
+
"lstrip": false,
|
1048 |
+
"normalized": false,
|
1049 |
+
"rstrip": false,
|
1050 |
+
"single_word": false,
|
1051 |
+
"special": false
|
1052 |
+
},
|
1053 |
+
"131": {
|
1054 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1055 |
+
"lstrip": false,
|
1056 |
+
"normalized": false,
|
1057 |
+
"rstrip": false,
|
1058 |
+
"single_word": false,
|
1059 |
+
"special": false
|
1060 |
+
},
|
1061 |
+
"132": {
|
1062 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1063 |
+
"lstrip": false,
|
1064 |
+
"normalized": false,
|
1065 |
+
"rstrip": false,
|
1066 |
+
"single_word": false,
|
1067 |
+
"special": false
|
1068 |
+
},
|
1069 |
+
"133": {
|
1070 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1071 |
+
"lstrip": false,
|
1072 |
+
"normalized": false,
|
1073 |
+
"rstrip": false,
|
1074 |
+
"single_word": false,
|
1075 |
+
"special": false
|
1076 |
+
},
|
1077 |
+
"134": {
|
1078 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1079 |
+
"lstrip": false,
|
1080 |
+
"normalized": false,
|
1081 |
+
"rstrip": false,
|
1082 |
+
"single_word": false,
|
1083 |
+
"special": false
|
1084 |
+
},
|
1085 |
+
"135": {
|
1086 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1087 |
+
"lstrip": false,
|
1088 |
+
"normalized": false,
|
1089 |
+
"rstrip": false,
|
1090 |
+
"single_word": false,
|
1091 |
+
"special": false
|
1092 |
+
},
|
1093 |
+
"136": {
|
1094 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1095 |
+
"lstrip": false,
|
1096 |
+
"normalized": false,
|
1097 |
+
"rstrip": false,
|
1098 |
+
"single_word": false,
|
1099 |
+
"special": false
|
1100 |
+
},
|
1101 |
+
"137": {
|
1102 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1103 |
+
"lstrip": false,
|
1104 |
+
"normalized": false,
|
1105 |
+
"rstrip": false,
|
1106 |
+
"single_word": false,
|
1107 |
+
"special": false
|
1108 |
+
},
|
1109 |
+
"138": {
|
1110 |
+
"content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
|
1111 |
+
"lstrip": false,
|
1112 |
+
"normalized": false,
|
1113 |
+
"rstrip": false,
|
1114 |
+
"single_word": false,
|
1115 |
+
"special": false
|
1116 |
+
},
|
1117 |
+
"169": {
|
1118 |
+
"content": "<table>",
|
1119 |
+
"lstrip": false,
|
1120 |
+
"normalized": false,
|
1121 |
+
"rstrip": false,
|
1122 |
+
"single_word": false,
|
1123 |
+
"special": false
|
1124 |
+
},
|
1125 |
+
"170": {
|
1126 |
+
"content": "<caption>",
|
1127 |
+
"lstrip": false,
|
1128 |
+
"normalized": false,
|
1129 |
+
"rstrip": false,
|
1130 |
+
"single_word": false,
|
1131 |
+
"special": false
|
1132 |
+
},
|
1133 |
+
"171": {
|
1134 |
+
"content": "<thead>",
|
1135 |
+
"lstrip": false,
|
1136 |
+
"normalized": false,
|
1137 |
+
"rstrip": false,
|
1138 |
+
"single_word": false,
|
1139 |
+
"special": false
|
1140 |
+
},
|
1141 |
+
"172": {
|
1142 |
+
"content": "<tbody>",
|
1143 |
+
"lstrip": false,
|
1144 |
+
"normalized": false,
|
1145 |
+
"rstrip": false,
|
1146 |
+
"single_word": false,
|
1147 |
+
"special": false
|
1148 |
+
},
|
1149 |
+
"173": {
|
1150 |
+
"content": "<tfoot>",
|
1151 |
+
"lstrip": false,
|
1152 |
+
"normalized": false,
|
1153 |
+
"rstrip": false,
|
1154 |
+
"single_word": false,
|
1155 |
+
"special": false
|
1156 |
+
},
|
1157 |
+
"174": {
|
1158 |
+
"content": "<tr>",
|
1159 |
+
"lstrip": false,
|
1160 |
+
"normalized": false,
|
1161 |
+
"rstrip": false,
|
1162 |
+
"single_word": false,
|
1163 |
+
"special": false
|
1164 |
+
},
|
1165 |
+
"175": {
|
1166 |
+
"content": "<th>",
|
1167 |
+
"lstrip": false,
|
1168 |
+
"normalized": false,
|
1169 |
+
"rstrip": false,
|
1170 |
+
"single_word": false,
|
1171 |
+
"special": false
|
1172 |
+
},
|
1173 |
+
"176": {
|
1174 |
+
"content": "<td>",
|
1175 |
+
"lstrip": false,
|
1176 |
+
"normalized": false,
|
1177 |
+
"rstrip": false,
|
1178 |
+
"single_word": false,
|
1179 |
+
"special": false
|
1180 |
+
},
|
1181 |
+
"177": {
|
1182 |
+
"content": "</table>",
|
1183 |
+
"lstrip": false,
|
1184 |
+
"normalized": false,
|
1185 |
+
"rstrip": false,
|
1186 |
+
"single_word": false,
|
1187 |
+
"special": false
|
1188 |
+
},
|
1189 |
+
"178": {
|
1190 |
+
"content": "</caption>",
|
1191 |
+
"lstrip": false,
|
1192 |
+
"normalized": false,
|
1193 |
+
"rstrip": false,
|
1194 |
+
"single_word": false,
|
1195 |
+
"special": false
|
1196 |
+
},
|
1197 |
+
"179": {
|
1198 |
+
"content": "</thead>",
|
1199 |
+
"lstrip": false,
|
1200 |
+
"normalized": false,
|
1201 |
+
"rstrip": false,
|
1202 |
+
"single_word": false,
|
1203 |
+
"special": false
|
1204 |
+
},
|
1205 |
+
"180": {
|
1206 |
+
"content": "</tbody>",
|
1207 |
+
"lstrip": false,
|
1208 |
+
"normalized": false,
|
1209 |
+
"rstrip": false,
|
1210 |
+
"single_word": false,
|
1211 |
+
"special": false
|
1212 |
+
},
|
1213 |
+
"181": {
|
1214 |
+
"content": "</tfoot>",
|
1215 |
+
"lstrip": false,
|
1216 |
+
"normalized": false,
|
1217 |
+
"rstrip": false,
|
1218 |
+
"single_word": false,
|
1219 |
+
"special": false
|
1220 |
+
},
|
1221 |
+
"182": {
|
1222 |
+
"content": "</tr>",
|
1223 |
+
"lstrip": false,
|
1224 |
+
"normalized": false,
|
1225 |
+
"rstrip": false,
|
1226 |
+
"single_word": false,
|
1227 |
+
"special": false
|
1228 |
+
},
|
1229 |
+
"183": {
|
1230 |
+
"content": "</th>",
|
1231 |
+
"lstrip": false,
|
1232 |
+
"normalized": false,
|
1233 |
+
"rstrip": false,
|
1234 |
+
"single_word": false,
|
1235 |
+
"special": false
|
1236 |
+
},
|
1237 |
+
"184": {
|
1238 |
+
"content": "</td>",
|
1239 |
+
"lstrip": false,
|
1240 |
+
"normalized": false,
|
1241 |
+
"rstrip": false,
|
1242 |
+
"single_word": false,
|
1243 |
+
"special": false
|
1244 |
+
},
|
1245 |
+
"185": {
|
1246 |
+
"content": "<h1>",
|
1247 |
+
"lstrip": false,
|
1248 |
+
"normalized": false,
|
1249 |
+
"rstrip": false,
|
1250 |
+
"single_word": false,
|
1251 |
+
"special": false
|
1252 |
+
},
|
1253 |
+
"186": {
|
1254 |
+
"content": "<h2>",
|
1255 |
+
"lstrip": false,
|
1256 |
+
"normalized": false,
|
1257 |
+
"rstrip": false,
|
1258 |
+
"single_word": false,
|
1259 |
+
"special": false
|
1260 |
+
},
|
1261 |
+
"187": {
|
1262 |
+
"content": "<h3>",
|
1263 |
+
"lstrip": false,
|
1264 |
+
"normalized": false,
|
1265 |
+
"rstrip": false,
|
1266 |
+
"single_word": false,
|
1267 |
+
"special": false
|
1268 |
+
},
|
1269 |
+
"188": {
|
1270 |
+
"content": "<h4>",
|
1271 |
+
"lstrip": false,
|
1272 |
+
"normalized": false,
|
1273 |
+
"rstrip": false,
|
1274 |
+
"single_word": false,
|
1275 |
+
"special": false
|
1276 |
+
},
|
1277 |
+
"189": {
|
1278 |
+
"content": "<h5>",
|
1279 |
+
"lstrip": false,
|
1280 |
+
"normalized": false,
|
1281 |
+
"rstrip": false,
|
1282 |
+
"single_word": false,
|
1283 |
+
"special": false
|
1284 |
+
},
|
1285 |
+
"190": {
|
1286 |
+
"content": "<h6>",
|
1287 |
+
"lstrip": false,
|
1288 |
+
"normalized": false,
|
1289 |
+
"rstrip": false,
|
1290 |
+
"single_word": false,
|
1291 |
+
"special": false
|
1292 |
+
},
|
1293 |
+
"191": {
|
1294 |
+
"content": "<blockquote>",
|
1295 |
+
"lstrip": false,
|
1296 |
+
"normalized": false,
|
1297 |
+
"rstrip": false,
|
1298 |
+
"single_word": false,
|
1299 |
+
"special": false
|
1300 |
+
},
|
1301 |
+
"192": {
|
1302 |
+
"content": "</h1>",
|
1303 |
+
"lstrip": false,
|
1304 |
+
"normalized": false,
|
1305 |
+
"rstrip": false,
|
1306 |
+
"single_word": false,
|
1307 |
+
"special": false
|
1308 |
+
},
|
1309 |
+
"193": {
|
1310 |
+
"content": "</h2>",
|
1311 |
+
"lstrip": false,
|
1312 |
+
"normalized": false,
|
1313 |
+
"rstrip": false,
|
1314 |
+
"single_word": false,
|
1315 |
+
"special": false
|
1316 |
+
},
|
1317 |
+
"194": {
|
1318 |
+
"content": "</h3>",
|
1319 |
+
"lstrip": false,
|
1320 |
+
"normalized": false,
|
1321 |
+
"rstrip": false,
|
1322 |
+
"single_word": false,
|
1323 |
+
"special": false
|
1324 |
+
},
|
1325 |
+
"195": {
|
1326 |
+
"content": "</h4>",
|
1327 |
+
"lstrip": false,
|
1328 |
+
"normalized": false,
|
1329 |
+
"rstrip": false,
|
1330 |
+
"single_word": false,
|
1331 |
+
"special": false
|
1332 |
+
},
|
1333 |
+
"196": {
|
1334 |
+
"content": "</h5>",
|
1335 |
+
"lstrip": false,
|
1336 |
+
"normalized": false,
|
1337 |
+
"rstrip": false,
|
1338 |
+
"single_word": false,
|
1339 |
+
"special": false
|
1340 |
+
},
|
1341 |
+
"197": {
|
1342 |
+
"content": "</h6>",
|
1343 |
+
"lstrip": false,
|
1344 |
+
"normalized": false,
|
1345 |
+
"rstrip": false,
|
1346 |
+
"single_word": false,
|
1347 |
+
"special": false
|
1348 |
+
},
|
1349 |
+
"198": {
|
1350 |
+
"content": "</blockquote>",
|
1351 |
+
"lstrip": false,
|
1352 |
+
"normalized": false,
|
1353 |
+
"rstrip": false,
|
1354 |
+
"single_word": false,
|
1355 |
+
"special": false
|
1356 |
+
},
|
1357 |
+
"199": {
|
1358 |
+
"content": "<strong>",
|
1359 |
+
"lstrip": false,
|
1360 |
+
"normalized": false,
|
1361 |
+
"rstrip": false,
|
1362 |
+
"single_word": false,
|
1363 |
+
"special": false
|
1364 |
+
},
|
1365 |
+
"200": {
|
1366 |
+
"content": "<em>",
|
1367 |
+
"lstrip": false,
|
1368 |
+
"normalized": false,
|
1369 |
+
"rstrip": false,
|
1370 |
+
"single_word": false,
|
1371 |
+
"special": false
|
1372 |
+
},
|
1373 |
+
"201": {
|
1374 |
+
"content": "<b>",
|
1375 |
+
"lstrip": false,
|
1376 |
+
"normalized": false,
|
1377 |
+
"rstrip": false,
|
1378 |
+
"single_word": false,
|
1379 |
+
"special": false
|
1380 |
+
},
|
1381 |
+
"202": {
|
1382 |
+
"content": "<i>",
|
1383 |
+
"lstrip": false,
|
1384 |
+
"normalized": false,
|
1385 |
+
"rstrip": false,
|
1386 |
+
"single_word": false,
|
1387 |
+
"special": false
|
1388 |
+
},
|
1389 |
+
"203": {
|
1390 |
+
"content": "<u>",
|
1391 |
+
"lstrip": false,
|
1392 |
+
"normalized": false,
|
1393 |
+
"rstrip": false,
|
1394 |
+
"single_word": false,
|
1395 |
+
"special": false
|
1396 |
+
},
|
1397 |
+
"204": {
|
1398 |
+
"content": "<s>",
|
1399 |
+
"lstrip": false,
|
1400 |
+
"normalized": false,
|
1401 |
+
"rstrip": false,
|
1402 |
+
"single_word": false,
|
1403 |
+
"special": false
|
1404 |
+
},
|
1405 |
+
"205": {
|
1406 |
+
"content": "<sub>",
|
1407 |
+
"lstrip": false,
|
1408 |
+
"normalized": false,
|
1409 |
+
"rstrip": false,
|
1410 |
+
"single_word": false,
|
1411 |
+
"special": false
|
1412 |
+
},
|
1413 |
+
"206": {
|
1414 |
+
"content": "<sup>",
|
1415 |
+
"lstrip": false,
|
1416 |
+
"normalized": false,
|
1417 |
+
"rstrip": false,
|
1418 |
+
"single_word": false,
|
1419 |
+
"special": false
|
1420 |
+
},
|
1421 |
+
"207": {
|
1422 |
+
"content": "<code>",
|
1423 |
+
"lstrip": false,
|
1424 |
+
"normalized": false,
|
1425 |
+
"rstrip": false,
|
1426 |
+
"single_word": false,
|
1427 |
+
"special": false
|
1428 |
+
},
|
1429 |
+
"208": {
|
1430 |
+
"content": "</strong>",
|
1431 |
+
"lstrip": false,
|
1432 |
+
"normalized": false,
|
1433 |
+
"rstrip": false,
|
1434 |
+
"single_word": false,
|
1435 |
+
"special": false
|
1436 |
+
},
|
1437 |
+
"209": {
|
1438 |
+
"content": "</em>",
|
1439 |
+
"lstrip": false,
|
1440 |
+
"normalized": false,
|
1441 |
+
"rstrip": false,
|
1442 |
+
"single_word": false,
|
1443 |
+
"special": false
|
1444 |
+
},
|
1445 |
+
"210": {
|
1446 |
+
"content": "</b>",
|
1447 |
+
"lstrip": false,
|
1448 |
+
"normalized": false,
|
1449 |
+
"rstrip": false,
|
1450 |
+
"single_word": false,
|
1451 |
+
"special": false
|
1452 |
+
},
|
1453 |
+
"211": {
|
1454 |
+
"content": "</i>",
|
1455 |
+
"lstrip": false,
|
1456 |
+
"normalized": false,
|
1457 |
+
"rstrip": false,
|
1458 |
+
"single_word": false,
|
1459 |
+
"special": false
|
1460 |
+
},
|
1461 |
+
"212": {
|
1462 |
+
"content": "</u>",
|
1463 |
+
"lstrip": false,
|
1464 |
+
"normalized": false,
|
1465 |
+
"rstrip": false,
|
1466 |
+
"single_word": false,
|
1467 |
+
"special": false
|
1468 |
+
},
|
1469 |
+
"213": {
|
1470 |
+
"content": "</s>",
|
1471 |
+
"lstrip": false,
|
1472 |
+
"normalized": false,
|
1473 |
+
"rstrip": false,
|
1474 |
+
"single_word": false,
|
1475 |
+
"special": false
|
1476 |
+
},
|
1477 |
+
"214": {
|
1478 |
+
"content": "</sub>",
|
1479 |
+
"lstrip": false,
|
1480 |
+
"normalized": false,
|
1481 |
+
"rstrip": false,
|
1482 |
+
"single_word": false,
|
1483 |
+
"special": false
|
1484 |
+
},
|
1485 |
+
"215": {
|
1486 |
+
"content": "</sup>",
|
1487 |
+
"lstrip": false,
|
1488 |
+
"normalized": false,
|
1489 |
+
"rstrip": false,
|
1490 |
+
"single_word": false,
|
1491 |
+
"special": false
|
1492 |
+
},
|
1493 |
+
"216": {
|
1494 |
+
"content": "</code>",
|
1495 |
+
"lstrip": false,
|
1496 |
+
"normalized": false,
|
1497 |
+
"rstrip": false,
|
1498 |
+
"single_word": false,
|
1499 |
+
"special": false
|
1500 |
+
}
|
1501 |
+
},
|
1502 |
+
"bos_token": "<bos>",
|
1503 |
+
"clean_up_tokenization_spaces": false,
|
1504 |
+
"eos_token": "<eos>",
|
1505 |
+
"model_max_length": 1000000000000000019884624838656,
|
1506 |
+
"pad_token": "<pad>",
|
1507 |
+
"sp_model_kwargs": {},
|
1508 |
+
"spaces_between_special_tokens": false,
|
1509 |
+
"tokenizer_class": "GemmaTokenizer",
|
1510 |
+
"unk_token": "<unk>",
|
1511 |
+
"use_default_system_prompt": false
|
1512 |
+
}
|
APA/8/__01__.ipynb
ADDED
@@ -0,0 +1,261 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"cell_type": "markdown",
|
5 |
+
"metadata": {},
|
6 |
+
"source": [
|
7 |
+
"---"
|
8 |
+
]
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"cell_type": "markdown",
|
12 |
+
"metadata": {},
|
13 |
+
"source": [
|
14 |
+
"> <center><a href='https://o-0268-kvnaditya-8620-o.web.app/documentation/apa.html'><h3>Artificial-Intelligence Programming Assistance using GenAI</h3></center></a>\n",
|
15 |
+
"> <hr>\n",
|
16 |
+
"> <center>K.V.N.Aditya</center>\n",
|
17 |
+
"> <br>\n",
|
18 |
+
"> <center>SurgeClasses || CMR Technical Campus</center>"
|
19 |
+
]
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"cell_type": "markdown",
|
23 |
+
"metadata": {},
|
24 |
+
"source": [
|
25 |
+
"---\n",
|
26 |
+
"---"
|
27 |
+
]
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"cell_type": "markdown",
|
31 |
+
"metadata": {},
|
32 |
+
"source": [
|
33 |
+
"### <center>importing modules</center>"
|
34 |
+
]
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"cell_type": "code",
|
38 |
+
"execution_count": null,
|
39 |
+
"metadata": {},
|
40 |
+
"outputs": [],
|
41 |
+
"source": [
|
42 |
+
"import os\n",
|
43 |
+
"import shutil\n",
|
44 |
+
"import google.generativeai as genai\n",
|
45 |
+
"from IPython.core.interactiveshell import InteractiveShell\n",
|
46 |
+
"from IPython.display import display, Markdown\n",
|
47 |
+
"from datetime import datetime, timezone"
|
48 |
+
]
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"cell_type": "markdown",
|
52 |
+
"metadata": {},
|
53 |
+
"source": [
|
54 |
+
"---"
|
55 |
+
]
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"cell_type": "markdown",
|
59 |
+
"metadata": {},
|
60 |
+
"source": [
|
61 |
+
"### <center>configuring 'ipynb'</center>"
|
62 |
+
]
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"cell_type": "code",
|
66 |
+
"execution_count": null,
|
67 |
+
"metadata": {},
|
68 |
+
"outputs": [],
|
69 |
+
"source": [
|
70 |
+
"InteractiveShell.ast_node_interactivity = \"all\"\n",
|
71 |
+
"_H_ = '-' * shutil.get_terminal_size().columns\n",
|
72 |
+
"_HH_ = '=' * shutil.get_terminal_size().columns"
|
73 |
+
]
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"cell_type": "markdown",
|
77 |
+
"metadata": {},
|
78 |
+
"source": [
|
79 |
+
"---"
|
80 |
+
]
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"cell_type": "markdown",
|
84 |
+
"metadata": {},
|
85 |
+
"source": [
|
86 |
+
"### <center>initializing path</center>"
|
87 |
+
]
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"cell_type": "code",
|
91 |
+
"execution_count": null,
|
92 |
+
"metadata": {},
|
93 |
+
"outputs": [],
|
94 |
+
"source": [
|
95 |
+
"DMA__APA = os.path.abspath('../../APA').replace('\\\\', '/')"
|
96 |
+
]
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"cell_type": "markdown",
|
100 |
+
"metadata": {},
|
101 |
+
"source": [
|
102 |
+
"---"
|
103 |
+
]
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"cell_type": "markdown",
|
107 |
+
"metadata": {},
|
108 |
+
"source": [
|
109 |
+
"### <center>defining `APA`</center>"
|
110 |
+
]
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"cell_type": "code",
|
114 |
+
"execution_count": null,
|
115 |
+
"metadata": {},
|
116 |
+
"outputs": [],
|
117 |
+
"source": [
|
118 |
+
"class cls__APA():\n",
|
119 |
+
" def __init__(_io_,*,args__api_key='',args__apa_config__temp=1,args_apa_config__top_p=1,args_apa_config__top_k=1,args_apa_config__max_op_tokns=88888888,args__google_gemini_model='gemini-1.5-pro-latest',args__op_1__io=1,args__op_1__p=1,args__init__op_1='APA'):\n",
|
120 |
+
" _io_.init__apa = \"The name of the System is 'Artificial-Intelligence Programming Assistance (APA)' tuned by 'K.V.N.Aditya' using 'Google Gemini-1.5-Pro\\n\\nTasks:\\n Code Evolution : for the passed input task, generate the code\\n Code Termination : for the passed input task with partial code, complete the code\\n Code Evaluation : for the passed input task and code, evaluate the code and debug the errors, if needed test the input and/or output codes with test-cases\\n Code Definition : for the passed input task and code, explain / summarize the code.\\n\\nExamples: \\n Code Evolution :\\n [ip] :: evolute code to print \\\"APA\\\"\\n [op] ::\\n def func__APA:\\n print(\\\"APA\\\")\\n Code Termination :\\n [ip] :: terminate code for printing \\\"APA\\\" `def func__APA():...`\\n [op] ::\\n def func__APA:\\n print(\\\"APA\\\")\\n Code Evaluation :\\n [ip] :: evaluate code for printing \\\"APA\\\" `def func__APA() print(\\\"APA\\\")`\\n [op] ::\\n def func__APA:\\n print(\\\"APA\\\")\\n evaluation(s):\\n expected \\\":\\\" after function name\\n Code Definition :\\n [ip] :: define code `def func__APA():print(\\\"APA\\\")`\\n [op] ::\\n the code consists of a function defined as 'func__APA' which print the string 'APA' as output from with-in the function.\\n\\nDefaults :\\n Programming Language : Python\\n Tasks :\\n Code Evolution : if none of the task instructed, generate random program.\\n Code Termination : \\n if the prompt/instruction consists of any comment or '...' in the code specifies to terminate/complete the code based on instructions, complete the code just below the comment or '...' and eliminate the comment or '...' from the generated output. if none specified, terminate/complete the code based on the prompt.\\n Code Evaluation : check errors and fix them. if test-cases are provided use them and return the output\\n Code Definition : return summarization\\n Prompts :\\n info(APA) : return \\\"Artificial-Intelligence Programming Assistance (APA) is a AI based Programming Assistance to assist with the tasks as 'Code Evolution', 'Code Termination', 'Code Evaluation', 'Code Definition'. '\\\"\\n help(APA) : return 'Tasks' and 'Examples' from main (not from Defaults)\\n Tasks :\\n Code Evolution : if prompt/instruction consists of the terms {evolute, generate}\\n Code Termination : if prompt/instruction consists of the terms {terminate, complete}\\n Code Evaluation : if prompt/instruction consists of the terms {evaluate, fix, check, warnings, errors, test-cases}\\n Code Definition : if prompt/instruction consists of the terms {define, summarize, explain}\\n OP__404 :\\n when there could be some unknown exception/error occurs at the System or there could be no generated output for the passed input prompt/instruction, return \\\"[OP__404]::OOPs !!!couldn't generate output for the input. This may be due to unknown exception/error occurs at the System or there could be no generated output for the passed input prompt/instruction or the prompt/instruction may consists of harmful prompt/instruction tokens that may leads to cyber attacks, damage/malfunction the computer/electronic devices, not secure for living-beings and the universe\\\". The default model output need to be eliminated and instead generate this 'OP__404'\\n\\nOutputs :\\n Tasks :\\n Code Evolution : Code\\n Code Termination : Code\\n Code Evaluation : Code and Evaluation Process\\n Code Definition : Summary or Explanation\\n The generated outputs must be within the scope and don't explain/summarize the code for the tasks {Code Evolution | Code Termination | Code Evaluation}. After the code at the end of response warn with \\\"\\nuse code with caution. generated using AI. may generate inaccurate outputs\\n\\\"\\n\\nStructure [Generation Pipeline] :\\n The prompt/instruction may consists of multiple tasks. The structure of the generation pipeline based on the Tasks must be in the following order :\\n Code Evolution\\n Code Termination\\n Code Evaluation\\n Code Definition\\n\\nExceptions:\\n Don't generate the code if the prompt/instruction consists of any of the harmful prompt/instruction tokens that may leads to cyber attacks, damage/malfunction the computer/electronic devices, not secure for living-beings and the universe. At this return the default 'OP__404' as an output.\"\n",
|
121 |
+
" _io_.exceptions = [{\"category\": \"HARM_CATEGORY_HARASSMENT\",\"threshold\": \"BLOCK_MEDIUM_AND_ABOVE\"},{\"category\": \"HARM_CATEGORY_HATE_SPEECH\",\"threshold\": \"BLOCK_MEDIUM_AND_ABOVE\"},{\"category\": \"HARM_CATEGORY_SEXUALLY_EXPLICIT\",\"threshold\": \"BLOCK_MEDIUM_AND_ABOVE\"},{\"category\": \"HARM_CATEGORY_DANGEROUS_CONTENT\",\"threshold\": \"BLOCK_MEDIUM_AND_ABOVE\"}]\n",
|
122 |
+
" _io_.api_key = genai.configure(api_key=args__api_key)\n",
|
123 |
+
" _io_.apa_config = {\"temperature\": args__apa_config__temp,\"top_p\": args_apa_config__top_p,\"top_k\": args_apa_config__top_k,\"max_output_tokens\": args_apa_config__max_op_tokns}\n",
|
124 |
+
" _io_.google_gemini_model = args__google_gemini_model\n",
|
125 |
+
" _io_.apa = genai.GenerativeModel(model_name=_io_.google_gemini_model,generation_config=_io_.apa_config,system_instruction=_io_.init__apa,safety_settings=_io_.exceptions)\n",
|
126 |
+
" _io_.io = _io_.apa.start_chat(history=[])\n",
|
127 |
+
" _io_.init__op_1 = args__init__op_1\n",
|
128 |
+
" _io_.op_1__io = args__op_1__io\n",
|
129 |
+
" _io_.op_1__p = args__op_1__p\n",
|
130 |
+
" def mtd__APA(_io_,*,args__io='info(APA)',args__p=1):\n",
|
131 |
+
" _io_.io.send_message(args__io)\n",
|
132 |
+
" if(args__p==1):\n",
|
133 |
+
" display(_HH_)\n",
|
134 |
+
" display('[input]')\n",
|
135 |
+
" display(Markdown(args__io))\n",
|
136 |
+
" display(_H_)\n",
|
137 |
+
" display('[output]')\n",
|
138 |
+
" display(Markdown(_io_.io.last.text))\n",
|
139 |
+
" display(_HH_)\n",
|
140 |
+
" if(_io_.op_1__io==1 or _io_.op_1__p==1):\n",
|
141 |
+
" if(not(os.path.exists(_io_.init__op_1))):\n",
|
142 |
+
" os.mkdir(f'{_io_.init__op_1}') \n",
|
143 |
+
" if(_io_.op_1__io==1):\n",
|
144 |
+
" with open(f'{_io_.init__op_1}/ip_op.io','a') as f:\n",
|
145 |
+
" f.write('\\n')\n",
|
146 |
+
" f.write(_HH_)\n",
|
147 |
+
" f.write('\\n')\n",
|
148 |
+
" f.write('[input]')\n",
|
149 |
+
" f.write('\\n')\n",
|
150 |
+
" f.write(args__io)\n",
|
151 |
+
" f.write('\\n')\n",
|
152 |
+
" f.write(_H_)\n",
|
153 |
+
" f.write('\\n')\n",
|
154 |
+
" f.write('[output]')\n",
|
155 |
+
" f.write('\\n')\n",
|
156 |
+
" f.write(_io_.io.last.text)\n",
|
157 |
+
" f.write('\\n')\n",
|
158 |
+
" f.write(_HH_)\n",
|
159 |
+
" f.write('\\n')\n",
|
160 |
+
" if(_io_.op_1__p==1):\n",
|
161 |
+
" with open(f'{_io_.init__op_1}/io_p.io','w') as f:\n",
|
162 |
+
" f.write(_HH_)\n",
|
163 |
+
" f.write('\\n')\n",
|
164 |
+
" f.write(_io_.io.history.__str__())\n",
|
165 |
+
" f.write('\\n')\n",
|
166 |
+
" f.write(_HH_)"
|
167 |
+
]
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"cell_type": "markdown",
|
171 |
+
"metadata": {},
|
172 |
+
"source": [
|
173 |
+
"---"
|
174 |
+
]
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"cell_type": "markdown",
|
178 |
+
"metadata": {},
|
179 |
+
"source": [
|
180 |
+
"### <center>pipelining `APA`</center>"
|
181 |
+
]
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"cell_type": "code",
|
185 |
+
"execution_count": null,
|
186 |
+
"metadata": {},
|
187 |
+
"outputs": [],
|
188 |
+
"source": [
|
189 |
+
"__io__ = 1\n",
|
190 |
+
"while(__io__):\n",
|
191 |
+
" __io__ = int(input('[ip]:[__io__]::{1}:continue|{0}:exit') or 0)\n",
|
192 |
+
" if(not(__io__)):\n",
|
193 |
+
" break\n",
|
194 |
+
" try:\n",
|
195 |
+
" api_key = input('[ip]::Google Gemini API-Key') or ''\n",
|
196 |
+
" apa_config__temp = int(input('[ip]::temperature') or 1)\n",
|
197 |
+
" apa_config__top_p = int(input('[ip]::top_p') or 1)\n",
|
198 |
+
" apa_config__top_k = int(input('[ip]::top_k') or 1)\n",
|
199 |
+
" apa_config__max_op_tokns = int(input('[ip]::max_output_tokens') or 88888888)\n",
|
200 |
+
" google_gemini_model = input('[ip]::Google Gemini Model') or 'gemini-1.5-pro-latest'\n",
|
201 |
+
" init__op_1 = input('[ip]::init__op_1') or 'APA'\n",
|
202 |
+
" dt = datetime.now(timezone.utc)\n",
|
203 |
+
" init__op_1 = 'APA'+'__'+str(dt.year)+str(dt.month)+str(dt.day)+str(dt.hour)+str(dt.minute)+str(dt.second)+str(dt.microsecond)\n",
|
204 |
+
" init__op_1 = f'{DMA__APA}/1/io__APA/{init__op_1}'\n",
|
205 |
+
" op_1__io = int(input('[ip]::op_1__io') or 1)\n",
|
206 |
+
" op_1__p = int(input('[ip]::op_1__p') or 1)\n",
|
207 |
+
" obj__APA = cls__APA(args__api_key=api_key,args__apa_config__temp=apa_config__temp,args_apa_config__top_p=apa_config__top_p,args_apa_config__top_k=apa_config__top_k,args_apa_config__max_op_tokns=apa_config__max_op_tokns,args__google_gemini_model=google_gemini_model,args__op_1__io=op_1__io,args__op_1__p=op_1__p,args__init__op_1=init__op_1)\n",
|
208 |
+
" display(_HH_)\n",
|
209 |
+
" display(f\"[logs]::initializing `io__APA` at '{init__op_1}'\")\n",
|
210 |
+
" display(_HH_)\n",
|
211 |
+
" except Exception as e:\n",
|
212 |
+
" display(_HH_)\n",
|
213 |
+
" display(f\"[logs]::\\n\\t{e}\")\n",
|
214 |
+
" display(_HH_)\n",
|
215 |
+
" break\n",
|
216 |
+
" _io_ = 1\n",
|
217 |
+
" while(_io_):\n",
|
218 |
+
" _io_ = int(input('[ip]:[_io_]::{1}:continue|{0}:exit') or 1)\n",
|
219 |
+
" if(not(_io_)):\n",
|
220 |
+
" break\n",
|
221 |
+
" try:\n",
|
222 |
+
" io = input('[ip]::io') or 'info(APA)'\n",
|
223 |
+
" p = int(input('[ip]::p') or 1)\n",
|
224 |
+
" obj__APA.mtd__APA(args__io=io,args__p=p)\n",
|
225 |
+
" except Exception as e:\n",
|
226 |
+
" display(_HH_)\n",
|
227 |
+
" display(f\"[logs]::\\n\\t{e}\")\n",
|
228 |
+
" display(_HH_)\n",
|
229 |
+
" break"
|
230 |
+
]
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"cell_type": "markdown",
|
234 |
+
"metadata": {},
|
235 |
+
"source": [
|
236 |
+
"---"
|
237 |
+
]
|
238 |
+
}
|
239 |
+
],
|
240 |
+
"metadata": {
|
241 |
+
"kernelspec": {
|
242 |
+
"display_name": "cmrtc__surge_classes__dsaiml",
|
243 |
+
"language": "python",
|
244 |
+
"name": "python3"
|
245 |
+
},
|
246 |
+
"language_info": {
|
247 |
+
"codemirror_mode": {
|
248 |
+
"name": "ipython",
|
249 |
+
"version": 3
|
250 |
+
},
|
251 |
+
"file_extension": ".py",
|
252 |
+
"mimetype": "text/x-python",
|
253 |
+
"name": "python",
|
254 |
+
"nbconvert_exporter": "python",
|
255 |
+
"pygments_lexer": "ipython3",
|
256 |
+
"version": "3.12.1"
|
257 |
+
}
|
258 |
+
},
|
259 |
+
"nbformat": 4,
|
260 |
+
"nbformat_minor": 2
|
261 |
+
}
|
APA/_/.env
ADDED
File without changes
|
APA/_/requirements.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
ipython==8.12.3
|
2 |
+
ipython==8.22.2
|
3 |
+
protobuf==5.26.1
|
BW__RGB/0/ip__img/0.jpg
ADDED
![]() |
BW__RGB/0/ip__img/1.jpg
ADDED
![]() |
BW__RGB/0/ip__img/10.jpg
ADDED
![]() |
BW__RGB/0/ip__img/100.jpg
ADDED
![]() |
BW__RGB/0/ip__img/101.jpg
ADDED
![]() |
BW__RGB/0/ip__img/102.jpg
ADDED
![]() |
BW__RGB/0/ip__img/103.jpg
ADDED
![]() |
BW__RGB/0/ip__img/104.jpg
ADDED
![]() |
BW__RGB/0/ip__img/105.jpg
ADDED
![]() |
BW__RGB/0/ip__img/106.jpg
ADDED
![]() |
BW__RGB/0/ip__img/107.jpg
ADDED
![]() |
BW__RGB/0/ip__img/108.jpg
ADDED
![]() |
BW__RGB/0/ip__img/109.jpg
ADDED
![]() |
BW__RGB/0/ip__img/11.jpg
ADDED
![]() |
BW__RGB/0/ip__img/110.jpg
ADDED
![]() |
BW__RGB/0/ip__img/111.jpg
ADDED
![]() |
BW__RGB/0/ip__img/112.jpg
ADDED
![]() |
BW__RGB/0/ip__img/113.jpg
ADDED
![]() |
BW__RGB/0/ip__img/114.jpg
ADDED
![]() |
BW__RGB/0/ip__img/115.jpg
ADDED
![]() |
BW__RGB/0/ip__img/116.jpg
ADDED
![]() |
BW__RGB/0/ip__img/117.jpg
ADDED
![]() |
BW__RGB/0/ip__img/118.jpg
ADDED
![]() |
BW__RGB/0/ip__img/119.jpg
ADDED
![]() |
BW__RGB/0/ip__img/12.jpg
ADDED
![]() |
BW__RGB/0/ip__img/120.jpg
ADDED
![]() |