hirundo 0.1.21__tar.gz → 0.2.3.post1__tar.gz

{hirundo-0.1.21 → hirundo-0.2.3.post1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hirundo
-Version: 0.1.21
+Version: 0.2.3.post1
 Summary: This package is used to interface with Hirundo's platform. It provides a simple API to optimize your ML datasets.
 Author-email: Hirundo <dev@hirundo.io>
 License: MIT License
@@ -18,7 +18,7 @@ Keywords: dataset,machine learning,data science,data engineering
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3
-Requires-Python: >=3.9
+Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: pyyaml>=6.0.1
@@ -34,8 +34,9 @@ Requires-Dist: httpx-sse>=0.4.0
 Requires-Dist: tqdm>=4.66.5
 Requires-Dist: h11>=0.16.0
 Requires-Dist: requests>=2.32.4
-Requires-Dist: urllib3>=2.5.0
+Requires-Dist: urllib3>=2.6.3
 Requires-Dist: setuptools>=78.1.1
+Requires-Dist: docutils<0.22.0
 Provides-Extra: dev
 Requires-Dist: pyyaml>=6.0.1; extra == "dev"
 Requires-Dist: types-PyYAML>=6.0.12; extra == "dev"
@@ -50,15 +51,18 @@ Requires-Dist: stamina>=24.2.0; extra == "dev"
 Requires-Dist: httpx-sse>=0.4.0; extra == "dev"
 Requires-Dist: pytest>=8.2.0; extra == "dev"
 Requires-Dist: pytest-asyncio>=0.23.6; extra == "dev"
-Requires-Dist: uv>=0.8.6; extra == "dev"
+Requires-Dist: uv>=0.9.6; extra == "dev"
 Requires-Dist: pre-commit>=3.7.1; extra == "dev"
+Requires-Dist: basedpyright==1.37.1; extra == "dev"
 Requires-Dist: virtualenv>=20.6.6; extra == "dev"
+Requires-Dist: authlib>=1.6.6; extra == "dev"
 Requires-Dist: ruff>=0.12.0; extra == "dev"
-Requires-Dist: bumpver; extra == "dev"
+Requires-Dist: bumpver>=2025.1131; extra == "dev"
 Requires-Dist: platformdirs>=4.3.6; extra == "dev"
-Requires-Dist: safety>=3.2.13; extra == "dev"
 Requires-Dist: cryptography>=44.0.1; extra == "dev"
 Requires-Dist: jinja2>=3.1.6; extra == "dev"
+Requires-Dist: filelock>=3.20.1; extra == "dev"
+Requires-Dist: marshmallow>=3.26.2; extra == "dev"
 Provides-Extra: docs
 Requires-Dist: sphinx>=7.4.7; extra == "docs"
 Requires-Dist: sphinx-autobuild>=2024.9.3; extra == "docs"
@@ -67,13 +71,17 @@ Requires-Dist: autodoc_pydantic>=2.2.0; extra == "docs"
 Requires-Dist: furo; extra == "docs"
 Requires-Dist: sphinx-multiversion; extra == "docs"
 Requires-Dist: esbonio; extra == "docs"
-Requires-Dist: starlette>=0.47.2; extra == "docs"
+Requires-Dist: starlette>=0.49.1; extra == "docs"
 Requires-Dist: markupsafe>=3.0.2; extra == "docs"
 Requires-Dist: jinja2>=3.1.6; extra == "docs"
 Provides-Extra: pandas
 Requires-Dist: pandas>=2.2.3; extra == "pandas"
 Provides-Extra: polars
 Requires-Dist: polars>=1.0.0; extra == "polars"
+Provides-Extra: transformers
+Requires-Dist: transformers>=4.57.3; extra == "transformers"
+Requires-Dist: peft>=0.18.1; extra == "transformers"
+Requires-Dist: accelerate>=1.12.0; extra == "transformers"
 Dynamic: license-file
 
 # Hirundo
@@ -145,7 +153,31 @@ You can install the codebase with a simple `pip install hirundo` to install the
 
 ## Usage
 
-Classification example:
+### Unlearning LLM behavior
+
+Make sure to install the `transformers` extra, i.e. `pip install hirundo[transformers]` or `uv pip install hirundo[transformers]` if you have `uv` installed which is much faster than `pip`.
+
+```python
+llm = LlmModel(
+    model_name="Nemotron-Flash-1B",
+    model_source=HuggingFaceTransformersModel(
+        model_name="nvidia/Nemotron-Flash-1B",
+    ),
+)
+llm_id = llm.create()
+run_info = BiasRunInfo(
+    bias_type=BiasType.ALL,
+)
+run_id = LlmUnlearningRun.launch(
+    llm_id,
+    run_info,
+)
+new_adapter = llm.get_hf_pipeline_for_run(run_id)
+```
+
+### Dataset QA
+
+#### Classification example:
 
 ```python
 from hirundo import (
@@ -182,7 +214,7 @@ results = test_dataset.check_run()
 print(results)
 ```
 
-Object detection example:
+#### Object detection example:
 
 ```python
 from hirundo import (
@@ -223,7 +255,7 @@ results = test_dataset.check_run()
 print(results)
 ```
 
-Note: Currently we only support the main CPython release 3.9, 3.10, 3.11, 3.12 & 3.13. PyPy support may be introduced in the future.
+Note: Currently we only support the main CPython release 3.10, 3.11, 3.12 & 3.13. PyPy support may be introduced in the future.
 
 ## Further documentation
 

{hirundo-0.1.21 → hirundo-0.2.3.post1}/README.md

@@ -67,7 +67,31 @@ You can install the codebase with a simple `pip install hirundo` to install the
 
 ## Usage
 
-Classification example:
+### Unlearning LLM behavior
+
+Make sure to install the `transformers` extra, i.e. `pip install hirundo[transformers]` or `uv pip install hirundo[transformers]` if you have `uv` installed which is much faster than `pip`.
+
+```python
+llm = LlmModel(
+    model_name="Nemotron-Flash-1B",
+    model_source=HuggingFaceTransformersModel(
+        model_name="nvidia/Nemotron-Flash-1B",
+    ),
+)
+llm_id = llm.create()
+run_info = BiasRunInfo(
+    bias_type=BiasType.ALL,
+)
+run_id = LlmUnlearningRun.launch(
+    llm_id,
+    run_info,
+)
+new_adapter = llm.get_hf_pipeline_for_run(run_id)
+```
+
+### Dataset QA
+
+#### Classification example:
 
 ```python
 from hirundo import (
@@ -104,7 +128,7 @@ results = test_dataset.check_run()
 print(results)
 ```
 
-Object detection example:
+#### Object detection example:
 
 ```python
 from hirundo import (
@@ -145,7 +169,7 @@ results = test_dataset.check_run()
 print(results)
 ```
 
-Note: Currently we only support the main CPython release 3.9, 3.10, 3.11, 3.12 & 3.13. PyPy support may be introduced in the future.
+Note: Currently we only support the main CPython release 3.10, 3.11, 3.12 & 3.13. PyPy support may be introduced in the future.
 
 ## Further documentation
 

{hirundo-0.1.21 → hirundo-0.2.3.post1}/hirundo/__init__.py

@@ -5,8 +5,8 @@ from .dataset_enum import (
 )
 from .dataset_qa import (
     ClassificationRunArgs,
-    Domain,
     HirundoError,
+    ModalityType,
     ObjectDetectionRunArgs,
     QADataset,
     RunArgs,
@@ -30,6 +30,15 @@ from .storage import (
     StorageGit,
     StorageS3,
 )
+from .unlearning_llm import (
+    BiasRunInfo,
+    BiasType,
+    HuggingFaceTransformersModel,
+    LlmModel,
+    LlmSources,
+    LlmUnlearningRun,
+    LocalTransformersModel,
+)
 from .unzip import load_df, load_from_zip
 
 __all__ = [
@@ -43,7 +52,7 @@ __all__ = [
     "KeylabsObjSegImages",
     "KeylabsObjSegVideo",
     "QADataset",
-    "Domain",
+    "ModalityType",
     "RunArgs",
     "ClassificationRunArgs",
     "ObjectDetectionRunArgs",
@@ -59,8 +68,15 @@ __all__ = [
     "StorageGit",
     "StorageConfig",
     "DatasetQAResults",
+    "BiasRunInfo",
+    "BiasType",
+    "HuggingFaceTransformersModel",
+    "LlmModel",
+    "LlmSources",
+    "LlmUnlearningRun",
+    "LocalTransformersModel",
     "load_df",
     "load_from_zip",
 ]
 
-__version__ = "0.1.21"
+__version__ = "0.2.3.post1"

{hirundo-0.1.21 → hirundo-0.2.3.post1}/hirundo/_constraints.py

@@ -1,5 +1,4 @@
 import re
-import typing
 from typing import TYPE_CHECKING
 
 from hirundo._urls import (
@@ -135,8 +134,8 @@ def validate_labeling_type(
 
 def validate_labeling_info(
     labeling_type: "LabelingType",
-    labeling_info: "typing.Union[LabelingInfo, list[LabelingInfo]]",
-    storage_config: "typing.Union[StorageConfig, ResponseStorageConfig]",
+    labeling_info: "LabelingInfo | list[LabelingInfo]",
+    storage_config: "StorageConfig | ResponseStorageConfig",
 ) -> None:
     """
     Validate the labeling info for a dataset

{hirundo-0.1.21 → hirundo-0.2.3.post1}/hirundo/_iter_sse_retrying.py

@@ -1,6 +1,5 @@
 import asyncio
 import time
-import typing
 import uuid
 from collections.abc import AsyncGenerator, Generator
 
@@ -15,13 +14,15 @@ from hirundo.logger import get_logger
 
 logger = get_logger(__name__)
 
+MAX_RETRIES = 50
+
 
 # Credit: https://github.com/florimondmanca/httpx-sse/blob/master/README.md#handling-reconnections
 def iter_sse_retrying(
     client: httpx.Client,
     method: str,
     url: str,
-    headers: typing.Optional[dict[str, str]] = None,
+    headers: dict[str, str] | None = None,
 ) -> Generator[ServerSentEvent, None, None]:
     if headers is None:
         headers = {}
@@ -41,7 +42,8 @@ def iter_sse_retrying(
             httpx.ReadError,
             httpx.RemoteProtocolError,
             urllib3.exceptions.ReadTimeoutError,
-        )
+        ),
+        attempts=MAX_RETRIES,
     )
     def _iter_sse():
         nonlocal last_event_id, reconnection_delay
@@ -105,7 +107,8 @@ async def aiter_sse_retrying(
             httpx.ReadError,
             httpx.RemoteProtocolError,
             urllib3.exceptions.ReadTimeoutError,
-        )
+        ),
+        attempts=MAX_RETRIES,
     )
     async def _iter_sse() -> AsyncGenerator[ServerSentEvent, None]:
         nonlocal last_event_id, reconnection_delay

hirundo-0.2.3.post1/hirundo/_llm_pipeline.py

@@ -0,0 +1,153 @@
+import importlib.util
+import tempfile
+import zipfile
+from pathlib import Path
+from typing import TYPE_CHECKING, cast
+
+from hirundo import HirundoError
+from hirundo._http import requests
+from hirundo._timeouts import DOWNLOAD_READ_TIMEOUT
+from hirundo.logger import get_logger
+
+if TYPE_CHECKING:
+    from torch import device as torch_device
+    from transformers.configuration_utils import PretrainedConfig
+    from transformers.modeling_utils import PreTrainedModel
+    from transformers.pipelines.base import Pipeline
+
+    from hirundo.unlearning_llm import LlmModel, LlmModelOut
+
+logger = get_logger(__name__)
+
+
+ZIP_FILE_CHUNK_SIZE = 50 * 1024 * 1024  # 50 MB
+REQUIRED_PACKAGES_FOR_PIPELINE = ["peft", "transformers", "accelerate"]
+
+
+def get_hf_pipeline_for_run_given_model(
+    llm: "LlmModel | LlmModelOut",
+    run_id: str,
+    config: "PretrainedConfig | None" = None,
+    device: "str | int | torch_device | None" = None,
+    device_map: str | dict[str, int | str] | None = None,
+    trust_remote_code: bool = False,
+    token: str | None = None,
+) -> "Pipeline":
+    for package in REQUIRED_PACKAGES_FOR_PIPELINE:
+        if importlib.util.find_spec(package) is None:
+            raise HirundoError(
+                f'{package} is not installed. Please install transformers extra with pip install "hirundo[transformers]"'
+            )
+    from peft import PeftModel
+    from transformers.models.auto.configuration_auto import AutoConfig
+    from transformers.models.auto.modeling_auto import (
+        MODEL_FOR_IMAGE_TEXT_TO_TEXT_MAPPING_NAMES,
+        AutoModelForCausalLM,
+        AutoModelForImageTextToText,
+    )
+    from transformers.models.auto.tokenization_auto import AutoTokenizer
+    from transformers.pipelines import pipeline
+
+    from hirundo.unlearning_llm import (
+        HuggingFaceTransformersModel,
+        HuggingFaceTransformersModelOutput,
+        LlmUnlearningRun,
+    )
+
+    run_results = LlmUnlearningRun.check_run_by_id(run_id)
+    if run_results is None:
+        raise HirundoError("No run results found")
+    result_payload = (
+        run_results.get("result", run_results)
+        if isinstance(run_results, dict)
+        else run_results
+    )
+    if isinstance(result_payload, dict):
+        result_url = result_payload.get("result")
+    else:
+        result_url = result_payload
+    if not isinstance(result_url, str):
+        raise HirundoError("Run results did not include a download URL")
+    # Stream the zip file download
+
+    zip_file_path = tempfile.NamedTemporaryFile(delete=False).name
+    with requests.get(
+        result_url,
+        timeout=DOWNLOAD_READ_TIMEOUT,
+        stream=True,
+    ) as r:
+        r.raise_for_status()
+        with open(zip_file_path, "wb") as zip_file:
+            for chunk in r.iter_content(chunk_size=ZIP_FILE_CHUNK_SIZE):
+                zip_file.write(chunk)
+        logger.info(
+            "Successfully downloaded the result zip file for run ID %s to %s",
+            run_id,
+            zip_file_path,
+        )
+
+    with tempfile.TemporaryDirectory() as temp_dir:
+        temp_dir_path = Path(temp_dir)
+        with zipfile.ZipFile(zip_file_path, "r") as zip_file:
+            zip_file.extractall(temp_dir_path)
+        # Attempt to load the tokenizer normally
+        base_model_name = (
+            llm.model_source.model_name
+            if isinstance(
+                llm.model_source,
+                HuggingFaceTransformersModel | HuggingFaceTransformersModelOutput,
+            )
+            else llm.model_source.local_path
+        )
+        token = (
+            llm.model_source.token
+            if isinstance(
+                llm.model_source,
+                HuggingFaceTransformersModel,
+            )
+            else token
+        )
+        tokenizer = AutoTokenizer.from_pretrained(
+            base_model_name,
+            token=token,
+            trust_remote_code=trust_remote_code,
+        )
+        if tokenizer.pad_token is None:
+            tokenizer.pad_token = tokenizer.eos_token
+        config = AutoConfig.from_pretrained(
+            base_model_name,
+            token=token,
+            trust_remote_code=trust_remote_code,
+        )
+        config_dict = config.to_dict() if hasattr(config, "to_dict") else config
+        is_multimodal = (
+            config_dict.get("model_type")
+            in MODEL_FOR_IMAGE_TEXT_TO_TEXT_MAPPING_NAMES.keys()
+        )
+        if is_multimodal:
+            base_model = AutoModelForImageTextToText.from_pretrained(
+                base_model_name,
+                token=token,
+                trust_remote_code=trust_remote_code,
+            )
+        else:
+            base_model = AutoModelForCausalLM.from_pretrained(
+                base_model_name,
+                token=token,
+                trust_remote_code=trust_remote_code,
+            )
+        model = cast(
+            "PreTrainedModel",
+            PeftModel.from_pretrained(
+                base_model, str(temp_dir_path / "unlearned_model_folder")
+            ),
+        )
+
+        return pipeline(
+            task="text-generation",
+            model=model,
+            tokenizer=tokenizer,
+            config=config,
+            device=device,
+            device_map=device_map,
+        )