Spaces:
Runtime error
Runtime error
File size: 8,924 Bytes
11bd448 25bf2cc aae10fc 25bf2cc 11bd448 b4f5e30 11bd448 25bf2cc aae10fc 11bd448 aae10fc 11bd448 aae10fc 11bd448 aae10fc 11bd448 25bf2cc 11bd448 25bf2cc 11bd448 25bf2cc 11bd448 25bf2cc 11bd448 25bf2cc aae10fc |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 |
import pytest
from unittest.mock import MagicMock
import markdown
from bs4 import BeautifulSoup
from compliance_checks import (
ComplianceSuite,
ModelProviderIdentityCheck, ModelProviderIdentityResult,
IntendedPurposeCheck, IntendedPurposeResult,
GeneralLimitationsCheck, GeneralLimitationsResult,
ComputationalRequirementsCheck, ComputationalRequirementsResult,
)
expected_infrastructure = """\
Jean Zay Public Supercomputer, provided by the French government.\
Hardware\
384 A100 80GB GPUs (48 nodes)\
Software\
Megatron-DeepSpeed (Github link)\
"""
class TestComplianceCheck:
@pytest.fixture
def provider_identity_model_card(self):
return """
# Model Card for Sample Model
Some random info...
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** Nima Boscarino
- **Model type:** Yada yada yada
"""
@pytest.fixture
def bad_provider_identity_model_card(self):
return """
# Model Card for Sample Model
Some random info...
## Model Details
### Model Description
- **Developed by:** [More Information Needed]
- **Model type:** Yada yada yada
"""
@pytest.fixture
def intended_purpose_model_card(self):
return """
# Model Card for Sample Model
Some random info...
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
Here is some info about direct uses...
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
Here is some info about out-of-scope uses...
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
"""
@pytest.fixture
def bad_intended_purpose_model_card(self):
return """
# Model Card for Sample Model
Some random info...
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
"""
@pytest.fixture
def general_limitations_model_card(self):
return """
# Model Card for Sample Model
## Some Random Header
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
Hello world! These are some risks...
## More Things
"""
@pytest.fixture
def bad_general_limitations_model_card(self):
return """
# Model Card for Sample Model
## Some Random Header
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
## More Things
"""
@pytest.fixture
def computational_requirements_model_card(self):
# Adapted from: https://huggingface.co/bigscience/bloom/blob/main/README.md
return """
# Model Card for Sample Model
## Some Random Header
## Technical Specifications
### Compute infrastructure
Jean Zay Public Supercomputer, provided by the French government.
#### Hardware
* 384 A100 80GB GPUs (48 nodes)
#### Software
* Megatron-DeepSpeed ([Github link](https://github.com/bigscience-workshop/Megatron-DeepSpeed))
</details>
## Intended Use
Etc..
"""
@pytest.fixture
def bad_computational_requirements_model_card(self):
# Adapted from: https://huggingface.co/bigscience/bloom/blob/main/README.md
return """
# Model Card for Sample Model
## Some Random Header
## Technical Specifications
### Compute infrastructure
[More Information Needed]
## Intended Use
Etc..
"""
@pytest.mark.parametrize("check,card,expected", [
(ModelProviderIdentityCheck(), "provider_identity_model_card", ModelProviderIdentityResult(
status=True,
provider="Nima Boscarino",
)),
(ModelProviderIdentityCheck(), "bad_provider_identity_model_card", ModelProviderIdentityResult()),
(IntendedPurposeCheck(), "intended_purpose_model_card", IntendedPurposeResult(
status=True,
direct_use="Here is some info about direct uses...",
downstream_use=None,
out_of_scope_use="Here is some info about out-of-scope uses...",
)),
(IntendedPurposeCheck(), "bad_intended_purpose_model_card", IntendedPurposeResult()),
(GeneralLimitationsCheck(), "general_limitations_model_card", GeneralLimitationsResult(
status=True,
limitations="Hello world! These are some risks..."
)),
(GeneralLimitationsCheck(), "bad_general_limitations_model_card", GeneralLimitationsResult()),
(ComputationalRequirementsCheck(), "computational_requirements_model_card", ComputationalRequirementsResult(
status=True,
requirements=expected_infrastructure,
)),
(ComputationalRequirementsCheck(), "bad_computational_requirements_model_card", ComputationalRequirementsResult()),
])
def test_run_checks(self, check, card, expected, request):
card = request.getfixturevalue(card)
model_card_html = markdown.markdown(card)
card_soup = BeautifulSoup(model_card_html, features="html.parser")
results = check.run_check(card_soup)
assert results == expected
class TestComplianceSuite:
@pytest.fixture
def mock_compliance_check(self):
mockComplianceCheck = MagicMock()
mockComplianceCheck.run_check = MagicMock(return_value=True)
return mockComplianceCheck
@pytest.fixture
def empty_compliance_suite(self):
return ComplianceSuite(
checks=[]
)
@pytest.fixture
def compliance_suite(self, mock_compliance_check):
return ComplianceSuite(
checks=[mock_compliance_check]
)
@pytest.fixture
def empty_compliance_results(self):
return []
@pytest.fixture
def compliance_results(self):
return [True]
def test_create_empty_compliance_suite(self, empty_compliance_suite):
assert len(empty_compliance_suite.checks) == 0
def test_create_compliance_suite(self, compliance_suite):
assert len(compliance_suite.checks) == 1
@pytest.mark.parametrize("suite,results", [
("empty_compliance_suite", "empty_compliance_results"),
("compliance_suite", "compliance_results")
])
def test_run_compliance_suite(self, suite, results, request):
suite: ComplianceSuite = request.getfixturevalue(suite)
results: list = request.getfixturevalue(results)
assert suite.run("") == results
for check in suite.checks:
check.run_check.assert_called_once()
class TestEndToEnd:
@pytest.mark.parametrize("card,fixture", [
("""
# Model Card for Sample Model
Some random info...
## Model Details
### Model Description
- **Developed by:** Nima Boscarino
- **Model type:** Yada yada yada
## Uses
### Direct Use
Here is some info about direct uses...
### Downstream Use [optional]
[More Information Needed]
### Out-of-Scope Use
Here is some info about out-of-scope uses...
## Bias, Risks, and Limitations
Hello world! These are some risks...
## Technical Specifications
### Compute infrastructure
Jean Zay Public Supercomputer, provided by the French government.
#### Hardware
* 384 A100 80GB GPUs (48 nodes)
#### Software
* Megatron-DeepSpeed ([Github link](https://github.com/bigscience-workshop/Megatron-DeepSpeed))
</details>
## More Things
""", False),
("bloom_card", True)
])
def test_end_to_end_compliance_suite(self, card, fixture, request):
if fixture:
card = request.getfixturevalue(card)
suite = ComplianceSuite(checks=[
ModelProviderIdentityCheck(),
IntendedPurposeCheck(),
GeneralLimitationsCheck(),
ComputationalRequirementsCheck()
])
results = suite.run(card)
assert all([r.status for r in results])
|