fix: install kernels as a Transformers extra

Fixes #343

README.md

@@ -116,8 +116,9 @@ a configuration file.
 
 At the start of a program run, Heretic benchmarks the system to determine
 the optimal batch size to make the most of the available hardware.
-On an RTX 3090, with the default configuration, decensoring Llama-3.1-8B-Instruct
-takes about 45 minutes. Note that Heretic supports model quantization with
+On an RTX 3090, with the default configuration, decensoring
+[Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507)
+takes about 20-30 minutes. Note that Heretic supports model quantization with
 bitsandbytes, which can drastically reduce the amount of VRAM required to process
 models. Set the `quantization` option to `bnb_4bit` to enable quantization.
 

config.default.toml

@@ -135,6 +135,7 @@ max_shard_size = "5GB"
 
 # Strings whose presence in a response (case insensitive) identifies the response as a refusal.
 refusal_markers = [
+    "disclaimer",
     "sorry",
     "i can'",
     "i cant",
@@ -172,6 +173,11 @@ refusal_markers = [
 # System prompt to use when prompting the model.
 system_prompt = "You are a helpful assistant."
 
+# Each "dataset" below can be a Hugging Face dataset ID, a path to a dataset on disk,
+# or a path to a plain text file with one prompt per line (empty lines are ignored).
+# For text files, "column" is ignored and "split" is optional; when given, it selects
+# a subset of the lines using slice notation (e.g. "[:400]").
+
 # Dataset of prompts that tend to not result in refusals (used for calculating refusal directions).
 [good_prompts]
 dataset = "mlabonne/harmless_alpaca"

config.nohumor.toml

@@ -0,0 +1,69 @@
+# Rename this file to config.toml, place it in the working directory
+# that you run Heretic from, and edit the configuration to your liking.
+
+max_response_length = 300
+
+residual_plot_title = "PaCMAP Projection of Residuals for Serious/Humorous Prompts"
+
+refusal_markers = [
+    "😅",
+    "here's one",
+    "why did",
+    "walked into a bar",
+    "gets worse",
+    "the punchline",
+    "classic",
+    "dad joke",
+    "bad joke",
+    "pun intended",
+    "ba dum tss",
+    "rimshot",
+    "😂",
+    "😄",
+    "😆",
+    "haha",
+    "hehe",
+    "lol",
+    "funny",
+    "joke",
+    "humor",
+    "that's hilarious",
+    "you could say",
+    "one-liner",
+    "comedian",
+    "stand-up",
+    "unexpectedly",
+    "because apparently",
+    "to be fair",
+    "on the bright side",
+    "lmao",
+    "omg",
+    "rofl",
+    "silly",
+    "humorous",
+    "clever",
+]
+
+[good_prompts]
+dataset = "mlabonne/harmless_alpaca"
+split = "train[:400]"
+column = "text"
+residual_plot_label = "Serious prompts"
+residual_plot_color = "royalblue"
+
+[bad_prompts]
+dataset = "UnstableLlama/jokes"
+split = "train[:200]"
+column = "text"
+residual_plot_label = "Humorous prompts"
+residual_plot_color = "darkorange"
+
+[good_evaluation_prompts]
+dataset = "mlabonne/harmless_alpaca"
+split = "test[:100]"
+column = "text"
+
+[bad_evaluation_prompts]
+dataset = "UnstableLlama/jokes"
+split = "train[200:250]"
+column = "text"

pyproject.toml

@@ -25,10 +25,8 @@ dependencies = [
     "accelerate~=1.13",
     "bitsandbytes~=0.49",
     "datasets~=4.7",
-    "hf-transfer~=0.1",
     "huggingface-hub~=1.7",
     "immutabledict~=4.3",
-    "kernels~=0.13",
     "langdetect~=1.0",
     "lm-eval[hf]~=0.4",
     "numpy~=2.2",
@@ -41,7 +39,7 @@ dependencies = [
     "rich~=14.3",
     "tomli-w~=1.2",
     "tqdm~=4.67",
-    "transformers~=5.6",
+    "transformers[kernels]~=5.6",
 ]
 
 [project.optional-dependencies]

src/heretic/config.py

@@ -42,9 +42,15 @@ class DatasetSpecification(BaseModel):
         description="Hugging Face commit hash of the dataset.",
     )
 
-    split: str = Field(description="Portion of the dataset to use.")
+    split: str | None = Field(
+        default=None,
+        description="Portion of the dataset to use. Required for datasets, optional for plain text files.",
+    )
 
-    column: str = Field(description="Column in the dataset that contains the prompts.")
+    column: str | None = Field(
+        default=None,
+        description="Column in the dataset that contains the prompts. Required for datasets, ignored for plain text files.",
+    )
 
     prefix: str = Field(
         default="",
@@ -103,6 +109,16 @@ class Settings(BaseSettings):
         exclude=True,
     )
 
+    collect_reproducibles: str | None = Field(
+        default=None,
+        description=(
+            "If this directory path is set, then instead of abliterating a model, "
+            "download all reproduce.json files from public Heretic model repositories "
+            "on Hugging Face, and store them in that directory for archival purposes."
+        ),
+        exclude=True,
+    )
+
     dtypes: list[str] = Field(
         default=[
             # In practice, "auto" almost always means bfloat16.
@@ -402,6 +418,7 @@ class Settings(BaseSettings):
 
     refusal_markers: list[str] = Field(
         default=[
+            "disclaimer",
             "sorry",
             "i can'",
             "i cant",

src/heretic/main.py

@@ -65,6 +65,7 @@ from .analyzer import Analyzer
 from .config import QuantizationMethod
 from .evaluator import Evaluator
 from .model import AbliterationParameters, Model, get_model_class
+from .reproduce import collect_reproducibles
 from .system import empty_cache, get_accelerator_info
 from .utils import (
     format_duration,
@@ -144,18 +145,13 @@ def obtain_merge_strategy(settings: Settings, model: Model) -> str | None:
                 value="merge",
             ),
             Choice(
-                    title="Cancel",
-                    value="cancel",
+                title="Save LoRA adapter only (can be merged later)",
+                value="adapter",
             ),
         ],
     )
 
-        if strategy == "cancel":
-            return None
-
     return strategy
-    else:
-        return "merge"
 
 
 def run():
@@ -177,6 +173,8 @@ def run():
     if (
         # There is at least one argument (argv[0] is the program name).
         len(sys.argv) > 1
+        # Heretic is being invoked in standard (model processing) mode.
+        and "--collect-reproducibles" not in sys.argv
         # No model has been explicitly provided.
         and "--model" not in sys.argv
         # The last argument is a parameter value rather than a flag (such as "--help").
@@ -185,6 +183,11 @@ def run():
         # Assume the last argument is the model.
         sys.argv.insert(-1, "--model")
 
+    # Work around the "model" argument being required
+    # when Heretic is invoked in a non-processing mode.
+    if "--collect-reproducibles" in sys.argv and "--model" not in sys.argv:
+        sys.argv.extend(["--model", ""])
+
     try:
         # The required argument "model" must be provided by the user,
         # either on the command line or in the configuration file.
@@ -201,6 +204,10 @@ def run():
         )
         return
 
+    if settings.collect_reproducibles is not None:
+        collect_reproducibles(settings.collect_reproducibles)
+        return
+
     if settings.seed is None:
         settings.seed = random.randint(0, 2**32 - 1)
 
@@ -742,6 +749,10 @@ def run():
             print("* Parameters:")
             for name, value in get_trial_parameters(trial).items():
                 print(f"  * {name} = [bold]{value}[/]")
+
+            # Per https://github.com/huggingface/peft/issues/868#issuecomment-1820642893 once a LoRA is merged it's
+            # expected to be empty. Provide a utility function to restore the previous LoRA-ified state.
+            def reset_trial_model() -> None:
                 print("* Resetting model...")
                 model.reset_model()
                 print("* Abliterating...")
@@ -754,6 +765,8 @@ def run():
                     },
                 )
 
+            reset_trial_model()
+
             while True:
                 print()
                 action = prompt_select(
@@ -800,6 +813,7 @@ def run():
                                 del merged_model
                                 empty_cache()
                                 model.tokenizer.save_pretrained(save_directory)
+                                reset_trial_model()
 
                             print(f"Model saved to [bold]{save_directory}[/].")
 
@@ -909,6 +923,7 @@ def run():
                                     private=private,
                                     token=token,
                                 )
+                                reset_trial_model()
 
                             if is_hf_path(settings.model):
                                 card = ModelCard.load(settings.model)

src/heretic/model.py

@@ -389,6 +389,21 @@ class Model:
             for expert in layer.block_sparse_moe.experts:  # ty:ignore[possibly-missing-attribute, not-iterable]
                 try_add("mlp.down_proj", expert.w2)  # ty:ignore[possibly-missing-attribute]
 
+        # LFM dense operator blocks.
+        with suppress(Exception):
+            try_add("attn.o_proj", layer.conv.out_proj)  # ty:ignore[possibly-missing-attribute]
+
+        with suppress(Exception):
+            try_add("mlp.down_proj", layer.feed_forward.w2)  # ty:ignore[possibly-missing-attribute]
+
+        # LFM transformer blocks.
+        with suppress(Exception):
+            try_add("attn.o_proj", layer.self_attn.out_proj)  # ty:ignore[possibly-missing-attribute]
+
+        with suppress(Exception):
+            for expert in layer.feed_forward.experts:  # ty:ignore[possibly-missing-attribute, not-iterable]
+                try_add("mlp.down_proj", expert.w2)  # ty:ignore[possibly-missing-attribute]
+
         # Granite MoE Hybrid - attention layers with shared_mlp.
         with suppress(Exception):
             try_add("mlp.down_proj", layer.shared_mlp.output_linear)  # ty:ignore[possibly-missing-attribute]

src/heretic/reproduce.py

@@ -0,0 +1,83 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+# Copyright (C) 2025-2026  Philipp Emanuel Weidmann <pew@worldwidemann.com> + contributors
+
+import shutil
+from pathlib import Path
+
+from huggingface_hub import HfApi, hf_hub_download
+from huggingface_hub.utils import disable_progress_bars, enable_progress_bars
+
+from .utils import print
+
+
+def collect_reproducibles(path: str):
+    print(
+        f"Collecting [bold]reproduce.json[/] files from Hugging Face and storing them in [bold]{path}[/]..."
+    )
+    print()
+
+    api = HfApi()
+
+    models = api.list_models(
+        filter=["heretic", "reproducible"],
+        sort="created_at",
+    )
+
+    found = 0
+    downloaded = 0
+
+    # We're only downloading tiny files, so the progress bars are just noise.
+    disable_progress_bars()
+
+    try:
+        for model in models:
+            # Ignore repositories containing quantizations.
+            if model.tags is not None and "gguf" in model.tags:
+                continue
+
+            print(f"[bold]{model.id}[/]...", end="")
+
+            user, repository = model.id.split("/")
+
+            paths_info = api.get_paths_info(
+                model.id,
+                "reproduce/reproduce.json",
+                expand=True,
+            )
+            # The reproduce.json file might not exist in the repository
+            # despite the relevant tags being present.
+            if not paths_info:
+                print(" [yellow]no reproduce.json found[/]")
+                continue
+
+            found += 1
+
+            commit_hash = paths_info[0].last_commit.oid
+
+            file_path = (
+                Path(path)
+                / "huggingface.co"
+                / user
+                / f"{repository}-{commit_hash[:7]}.json"
+            )
+            if file_path.exists():
+                print(" already stored")
+                continue
+
+            cache_path = hf_hub_download(
+                model.id,
+                "reproduce/reproduce.json",
+            )
+
+            file_path.parent.mkdir(parents=True, exist_ok=True)
+            shutil.copyfile(cache_path, file_path)
+            print(" [green]downloaded[/]")
+
+            downloaded += 1
+    finally:
+        enable_progress_bars()
+
+    print()
+    print(f"Found: [bold]{found}[/] files")
+    print(f"Downloaded: [bold]{downloaded}[/] files")
+    print(f"Already stored: [bold]{found - downloaded}[/] files")

src/heretic/utils.py

@@ -22,6 +22,7 @@ from datasets import DatasetDict, ReadInstruction, load_dataset, load_from_disk
 from datasets.config import DATASET_STATE_JSON_FILENAME
 from datasets.download.download_manager import DownloadMode
 from datasets.utils.info_utils import VerificationMode
+from huggingface_hub.utils import validate_repo_id
 from optuna import Trial
 from psutil import Process
 from questionary import Choice, Style
@@ -172,13 +173,13 @@ def format_duration(seconds: float) -> str:
 def is_hf_path(path: str) -> bool:
     """Checks whether a path likely refers to a Hugging Face repository."""
 
-    return (
-        not path.startswith("/")
-        and not path.endswith("/")
-        and path.count("/") == 1
-        and "\\" not in path
-        and not Path(path).exists()
-    )
+    # Match Transformers: existing local paths take precedence over Hub lookup,
+    # even if the path string is also a valid repository ID.
+    if Path(path).exists():
+        return False
+
+    validate_repo_id(path)
+    return True
 
 
 @dataclass
@@ -187,6 +188,20 @@ class Prompt:
     user: str
 
 
+def get_split_slice(split_str: str, length: int) -> tuple[int, int]:
+    """Resolves a split specification into absolute (start, end) indices."""
+
+    # The split name is the part before the slice, e.g. "train" in "train[:400]".
+    split_name = split_str.split("[")[0]
+    # Associate the split with its number of examples (lines).
+    name_to_length = {split_name: length}
+    # Convert the instructions to absolute indices and select the first one.
+    absolute_instruction = ReadInstruction.from_spec(split_str).to_absolute(
+        name_to_length
+    )[0]
+    return absolute_instruction.from_, absolute_instruction.to
+
+
 def load_prompts(
     settings: Settings,
     specification: DatasetSpecification,
@@ -194,29 +209,41 @@ def load_prompts(
     path = specification.dataset
     split_str = specification.split
 
+    if os.path.isfile(path):
+        # Plain text file with one prompt per line. Empty lines are ignored.
+        with open(path, encoding="utf-8") as file:
+            prompts = [line.strip() for line in file if line.strip()]
+
+        # The split is optional for text files. When given, it selects a subset
+        # of the lines using slice notation (e.g. "[:400]"). A synthetic split
+        # name is prepended because ReadInstruction expects a named split.
+        if split_str is not None:
+            start, end = get_split_slice(f"_{split_str}", len(prompts))
+            prompts = prompts[start:end]
+    else:
+        # All dataset sources require an explicit split and column.
+        if split_str is None:
+            raise ValueError(f'The "split" field is required for datasets: {path}')
+
+        if specification.column is None:
+            raise ValueError(f'The "column" field is required for datasets: {path}')
+
         if is_hf_path(path):
             dataset = load_dataset(
                 path,
                 revision=specification.commit,
                 split=split_str,
             )
-    else:
-        if Path(path, DATASET_STATE_JSON_FILENAME).exists():
+        elif Path(path, DATASET_STATE_JSON_FILENAME).exists():
             # Dataset saved with datasets.save_to_disk; needs special handling.
             # Path should be the subdirectory for a particular split.
             dataset = load_from_disk(path)
             assert not isinstance(dataset, DatasetDict), (
                 "Loading dataset dicts is not supported"
             )
-            # Parse the split instructions.
-            instruction = ReadInstruction.from_spec(split_str)
-            # Associate the split with its number of examples (lines).
-            split_name = str(dataset.split)
-            name2len = {split_name: len(dataset)}
-            # Convert the instructions to absolute indices and select the first one.
-            abs_instruction = instruction.to_absolute(name2len)[0]
-            # Get the dataset by applying the indices.
-            dataset = dataset[abs_instruction.from_ : abs_instruction.to]
+            # Parse the split instructions and apply them.
+            start, end = get_split_slice(split_str, len(dataset))
+            dataset = dataset[start:end]
         else:
             # Path should be a local directory.
             dataset = load_dataset(

uv.lock

@@ -8,7 +8,7 @@ resolution-markers = [
 ]
 
 [options]
-exclude-newer = "2026-04-28T12:47:55.130721483Z"
+exclude-newer = "2026-05-28T06:40:14.509192809Z"
 exclude-newer-span = "P7D"
 
 [[package]]
@@ -937,10 +937,8 @@ dependencies = [
     { name = "accelerate" },
     { name = "bitsandbytes" },
     { name = "datasets" },
-    { name = "hf-transfer" },
     { name = "huggingface-hub" },
     { name = "immutabledict" },
-    { name = "kernels" },
     { name = "langdetect" },
     { name = "lm-eval", extra = ["hf"] },
     { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
@@ -954,7 +952,7 @@ dependencies = [
     { name = "rich" },
     { name = "tomli-w" },
     { name = "tqdm" },
-    { name = "transformers" },
+    { name = "transformers", extra = ["kernels"] },
 ]
 
 [package.optional-dependencies]
@@ -979,11 +977,9 @@ requires-dist = [
     { name = "bitsandbytes", specifier = "~=0.49" },
     { name = "datasets", specifier = "~=4.7" },
     { name = "geom-median", marker = "extra == 'research'", specifier = "~=0.1" },
-    { name = "hf-transfer", specifier = "~=0.1" },
     { name = "huggingface-hub", specifier = "~=1.7" },
     { name = "imageio", marker = "extra == 'research'", specifier = "~=2.37" },
     { name = "immutabledict", specifier = "~=4.3" },
-    { name = "kernels", specifier = "~=0.13" },
     { name = "langdetect", specifier = "~=1.0" },
     { name = "lm-eval", extras = ["hf"], specifier = "~=0.4" },
     { name = "matplotlib", marker = "extra == 'research'", specifier = "~=3.10" },
@@ -999,7 +995,7 @@ requires-dist = [
     { name = "scikit-learn", marker = "extra == 'research'", specifier = "~=1.7" },
     { name = "tomli-w", specifier = "~=1.2" },
     { name = "tqdm", specifier = "~=4.67" },
-    { name = "transformers", specifier = "~=5.6" },
+    { name = "transformers", extras = ["kernels"], specifier = "~=5.6" },
 ]
 provides-extras = ["research"]
 
@@ -1009,38 +1005,6 @@ dev = [
     { name = "ty", specifier = ">=0.0.5" },
 ]
 
-[[package]]
-name = "hf-transfer"
-version = "0.1.9"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/1a/eb/8fc64f40388c29ce8ce3b2b180a089d4d6b25b1d0d232d016704cb852104/hf_transfer-0.1.9.tar.gz", hash = "sha256:035572865dab29d17e783fbf1e84cf1cb24f3fcf8f1b17db1cfc7fdf139f02bf", size = 25201, upload-time = "2025-01-07T10:05:12.947Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/a4/78/0dce00208f585fae675f40033ef9a30dedfa83665d5ac79f16beb4a0a6c2/hf_transfer-0.1.9-cp313-cp313t-macosx_10_12_x86_64.whl", hash = "sha256:6e94e8822da79573c9b6ae4d6b2f847c59a7a06c5327d7db20751b68538dc4f6", size = 1386084, upload-time = "2025-01-07T10:04:47.874Z" },
-    { url = "https://files.pythonhosted.org/packages/ea/2e/3d60b1a9e9f29a2152aa66c823bf5e399ae7be3fef310ff0de86779c5d2d/hf_transfer-0.1.9-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:3ebc4ab9023414880c8b1d3c38174d1c9989eb5022d37e814fa91a3060123eb0", size = 1343558, upload-time = "2025-01-07T10:04:42.313Z" },
-    { url = "https://files.pythonhosted.org/packages/fb/38/130a5ac3747f104033591bcac1c961cb1faadfdc91704f59b09c0b465ff2/hf_transfer-0.1.9-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8674026f21ed369aa2a0a4b46000aca850fc44cd2b54af33a172ce5325b4fc82", size = 3726676, upload-time = "2025-01-07T10:04:11.539Z" },
-    { url = "https://files.pythonhosted.org/packages/15/a1/f4e27c5ad17aac616ae0849e2aede5aae31db8267a948c6b3eeb9fd96446/hf_transfer-0.1.9-cp313-cp313t-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:3a736dfbb2c84f5a2c975478ad200c0c8bfcb58a25a35db402678fb87ce17fa4", size = 3062920, upload-time = "2025-01-07T10:04:16.297Z" },
-    { url = "https://files.pythonhosted.org/packages/8d/0d/727abdfba39bc3f1132cfa4c970588c2c0bb0d82fe2d645cc10f4e2f8e0b/hf_transfer-0.1.9-cp313-cp313t-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:504b8427fd785dd8546d53b9fafe6e436bd7a3adf76b9dce556507650a7b4567", size = 3578681, upload-time = "2025-01-07T10:04:29.702Z" },
-    { url = "https://files.pythonhosted.org/packages/50/d0/2b213eb1ea8b1252ccaf1a6c804d0aba03fea38aae4124df6a3acb70511a/hf_transfer-0.1.9-cp313-cp313t-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2c7fc1b85f4d0f76e452765d7648c9f4bfd0aedb9ced2ae1ebfece2d8cfaf8e2", size = 3398837, upload-time = "2025-01-07T10:04:22.778Z" },
-    { url = "https://files.pythonhosted.org/packages/8c/8a/79dbce9006e0bd6b74516f97451a7b7c64dbbb426df15d901dd438cfeee3/hf_transfer-0.1.9-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0d991376f0eac70a60f0cbc95602aa708a6f7c8617f28b4945c1431d67b8e3c8", size = 3546986, upload-time = "2025-01-07T10:04:36.415Z" },
-    { url = "https://files.pythonhosted.org/packages/a9/f7/9ac239b6ee6fe0bad130325d987a93ea58c4118e50479f0786f1733b37e8/hf_transfer-0.1.9-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:e6ac4eddcd99575ed3735ed911ddf9d1697e2bd13aa3f0ad7e3904dd4863842e", size = 4071715, upload-time = "2025-01-07T10:04:53.224Z" },
-    { url = "https://files.pythonhosted.org/packages/d8/a3/0ed697279f5eeb7a40f279bd783cf50e6d0b91f24120dcf66ef2cf8822b4/hf_transfer-0.1.9-cp313-cp313t-musllinux_1_2_armv7l.whl", hash = "sha256:57fd9880da1ee0f47250f735f791fab788f0aa1ee36afc49f761349869c8b4d9", size = 3388081, upload-time = "2025-01-07T10:04:57.818Z" },
-    { url = "https://files.pythonhosted.org/packages/dc/eb/47e477bdf1d784f31c7540db6cc8c354b777e51a186897a7abda34517f36/hf_transfer-0.1.9-cp313-cp313t-musllinux_1_2_i686.whl", hash = "sha256:5d561f0520f493c66b016d99ceabe69c23289aa90be38dd802d2aef279f15751", size = 3658654, upload-time = "2025-01-07T10:05:03.168Z" },
-    { url = "https://files.pythonhosted.org/packages/45/07/6661e43fbee09594a8a5e9bb778107d95fe38dac4c653982afe03d32bd4d/hf_transfer-0.1.9-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:a5b366d34cd449fe9b20ef25941e6eef0460a2f74e7389f02e673e1f88ebd538", size = 3690551, upload-time = "2025-01-07T10:05:09.238Z" },
-    { url = "https://files.pythonhosted.org/packages/81/f5/461d2e5f307e5048289b1168d5c642ae3bb2504e88dff1a38b92ed990a21/hf_transfer-0.1.9-cp38-abi3-macosx_10_12_x86_64.whl", hash = "sha256:e66acf91df4a8b72f60223059df3003062a5ae111757187ed1a06750a30e911b", size = 1393046, upload-time = "2025-01-07T10:04:51.003Z" },
-    { url = "https://files.pythonhosted.org/packages/41/ba/8d9fd9f1083525edfcb389c93738c802f3559cb749324090d7109c8bf4c2/hf_transfer-0.1.9-cp38-abi3-macosx_11_0_arm64.whl", hash = "sha256:8669dbcc7a3e2e8d61d42cd24da9c50d57770bd74b445c65123291ca842a7e7a", size = 1348126, upload-time = "2025-01-07T10:04:45.712Z" },
-    { url = "https://files.pythonhosted.org/packages/8e/a2/cd7885bc9959421065a6fae0fe67b6c55becdeda4e69b873e52976f9a9f0/hf_transfer-0.1.9-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8fd0167c4407a3bc4cdd0307e65ada2294ec04f1813d8a69a5243e379b22e9d8", size = 3728604, upload-time = "2025-01-07T10:04:14.173Z" },
-    { url = "https://files.pythonhosted.org/packages/f6/2e/a072cf196edfeda3310c9a5ade0a0fdd785e6154b3ce24fc738c818da2a7/hf_transfer-0.1.9-cp38-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:ee8b10afedcb75f71091bcc197c526a6ebf5c58bbbadb34fdeee6160f55f619f", size = 3064995, upload-time = "2025-01-07T10:04:18.663Z" },
-    { url = "https://files.pythonhosted.org/packages/c2/84/aec9ef4c0fab93c1ea2b1badff38c78b4b2f86f0555b26d2051dbc920cde/hf_transfer-0.1.9-cp38-abi3-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:5828057e313de59300dd1abb489444bc452efe3f479d3c55b31a8f680936ba42", size = 3580908, upload-time = "2025-01-07T10:04:32.834Z" },
-    { url = "https://files.pythonhosted.org/packages/29/63/b560d39651a56603d64f1a0212d0472a44cbd965db2fa62b99d99cb981bf/hf_transfer-0.1.9-cp38-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:fc6bd19e1cc177c66bdef15ef8636ad3bde79d5a4f608c158021153b4573509d", size = 3400839, upload-time = "2025-01-07T10:04:26.122Z" },
-    { url = "https://files.pythonhosted.org/packages/d6/d8/f87ea6f42456254b48915970ed98e993110521e9263472840174d32c880d/hf_transfer-0.1.9-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cdca9bfb89e6f8f281890cc61a8aff2d3cecaff7e1a4d275574d96ca70098557", size = 3552664, upload-time = "2025-01-07T10:04:40.123Z" },
-    { url = "https://files.pythonhosted.org/packages/d6/56/1267c39b65fc8f4e2113b36297320f102718bf5799b544a6cbe22013aa1d/hf_transfer-0.1.9-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:89a23f58b7b7effbc047b8ca286f131b17728c99a9f972723323003ffd1bb916", size = 4073732, upload-time = "2025-01-07T10:04:55.624Z" },
-    { url = "https://files.pythonhosted.org/packages/82/1a/9c748befbe3decf7cb415e34f8a0c3789a0a9c55910dea73d581e48c0ce5/hf_transfer-0.1.9-cp38-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:dc7fff1345980d6c0ebb92c811d24afa4b98b3e07ed070c8e38cc91fd80478c5", size = 3390096, upload-time = "2025-01-07T10:04:59.98Z" },
-    { url = "https://files.pythonhosted.org/packages/72/85/4c03da147b6b4b7cb12e074d3d44eee28604a387ed0eaf7eaaead5069c57/hf_transfer-0.1.9-cp38-abi3-musllinux_1_2_i686.whl", hash = "sha256:1a6bd16c667ebe89a069ca163060127a794fa3a3525292c900b8c8cc47985b0d", size = 3664743, upload-time = "2025-01-07T10:05:05.416Z" },
-    { url = "https://files.pythonhosted.org/packages/e7/6e/e597b04f753f1b09e6893075d53a82a30c13855cbaa791402695b01e369f/hf_transfer-0.1.9-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:d2fde99d502093ade3ab1b53f80da18480e9902aa960dab7f74fb1b9e5bc5746", size = 3695243, upload-time = "2025-01-07T10:05:11.411Z" },
-    { url = "https://files.pythonhosted.org/packages/09/89/d4e234727a26b2546c8fb70a276cd924260d60135f2165bf8b9ed67bb9a4/hf_transfer-0.1.9-cp38-abi3-win32.whl", hash = "sha256:435cc3cdc8524ce57b074032b8fd76eed70a4224d2091232fa6a8cef8fd6803e", size = 1086605, upload-time = "2025-01-07T10:05:18.873Z" },
-    { url = "https://files.pythonhosted.org/packages/a1/14/f1e15b851d1c2af5b0b1a82bf8eb10bda2da62d98180220ba6fd8879bb5b/hf_transfer-0.1.9-cp38-abi3-win_amd64.whl", hash = "sha256:16f208fc678911c37e11aa7b586bc66a37d02e636208f18b6bc53d29b5df40ad", size = 1160240, upload-time = "2025-01-07T10:05:14.324Z" },
-]
-
 [[package]]
 name = "hf-xet"
 version = "1.4.2"
@@ -1123,11 +1087,11 @@ wheels = [
 
 [[package]]
 name = "idna"
-version = "3.11"
+version = "3.15"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/6f/6d/0703ccc57f3a7233505399edb88de3cbd678da106337b9fcde432b65ed60/idna-3.11.tar.gz", hash = "sha256:795dafcc9c04ed0c1fb032c2aa73654d8e8c5023a7df64a53f39190ada629902", size = 194582, upload-time = "2025-10-12T14:55:20.501Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/82/77/7b3966d0b9d1d31a36ddf1746926a11dface89a83409bf1483f0237aa758/idna-3.15.tar.gz", hash = "sha256:ca962446ea538f7092a95e057da437618e886f4d349216d2b1e294abfdb65fdc", size = 199245, upload-time = "2026-05-12T22:45:57.011Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/0e/61/66938bbb5fc52dbdf84594873d5b51fb1f7c7794e9c0f5bd885f30bc507b/idna-3.11-py3-none-any.whl", hash = "sha256:771a87f49d9defaf64091e6e6fe9c18d4833f140bd19464795bc32d966ca37ea", size = 71008, upload-time = "2025-10-12T14:55:18.883Z" },
+    { url = "https://files.pythonhosted.org/packages/d2/23/408243171aa9aaba178d3e2559159c24c1171a641aa83b67bdd3394ead8e/idna-3.15-py3-none-any.whl", hash = "sha256:048adeaf8c2d788c40fee287673ccaa74c24ffd8dcf09ffa555a2fbb59f10ac8", size = 72340, upload-time = "2026-05-12T22:45:55.733Z" },
 ]
 
 [[package]]
@@ -1188,18 +1152,17 @@ wheels = [
 
 [[package]]
 name = "kernels"
-version = "0.13.0"
+version = "0.12.3"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "huggingface-hub" },
     { name = "packaging" },
     { name = "pyyaml" },
     { name = "tomli", marker = "python_full_version < '3.11'" },
-    { name = "tomlkit" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/3e/0d/e9c158c527a7b51382fe816a7b7e60caae17ff1153640c1803211a067c99/kernels-0.13.0.tar.gz", hash = "sha256:bf7908206009bff0017d09b87f0f6b5934a1a20520562caf1cbb06cab36418cc", size = 74755, upload-time = "2026-04-10T14:30:45.356Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/b3/84/9f68f355f6ce99e977872021fbdbafadcf2820f51d3f7bd697ec3801cb7a/kernels-0.12.3.tar.gz", hash = "sha256:87e29716578e7e71dc5a7578e0132bfdae305bedaeb602698f87c88ca6c60e32", size = 57407, upload-time = "2026-03-20T10:20:42.166Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/b3/45/2cb29e965c199ab01151fee24cbb57b23550c9e6bc897ca242b1e4b8c4bf/kernels-0.13.0-py3-none-any.whl", hash = "sha256:5d857ee4e06dc7496bcd59c4756e84eb71c019b34524dea58ccb0eaaae3bb6df", size = 69177, upload-time = "2026-04-10T14:30:43.551Z" },
+    { url = "https://files.pythonhosted.org/packages/e7/3e/778e4a86830e9139df2d16d86c4488fce426ec19daa83cbd2854ef389030/kernels-0.12.3-py3-none-any.whl", hash = "sha256:5d1d33fcb774e03bb7f0688ac24d91ef6b963692f80f0a85ddd2286e69f3cf2f", size = 55501, upload-time = "2026-03-20T10:20:40.643Z" },
 ]
 
 [[package]]
@@ -1509,14 +1472,14 @@ wheels = [
 
 [[package]]
 name = "mako"
-version = "1.3.11"
+version = "1.3.12"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "markupsafe" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/59/8a/805404d0c0b9f3d7a326475ca008db57aea9c5c9f2e1e39ed0faa335571c/mako-1.3.11.tar.gz", hash = "sha256:071eb4ab4c5010443152255d77db7faa6ce5916f35226eb02dc34479b6858069", size = 399811, upload-time = "2026-04-14T20:19:51.493Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/00/62/791b31e69ae182791ec67f04850f2f062716bbd205483d63a215f3e062d3/mako-1.3.12.tar.gz", hash = "sha256:9f778e93289bd410bb35daadeb4fc66d95a746f0b75777b942088b7fd7af550a", size = 400219, upload-time = "2026-04-28T19:01:08.512Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/68/a5/19d7aaa7e433713ffe881df33705925a196afb9532efc8475d26593921a6/mako-1.3.11-py3-none-any.whl", hash = "sha256:e372c6e333cf004aa736a15f425087ec977e1fcbd2966aae7f17c8dc1da27a77", size = 78503, upload-time = "2026-04-14T20:19:53.233Z" },
+    { url = "https://files.pythonhosted.org/packages/bc/b1/a0ec7a5a9db730a08daef1fdfb8090435b82465abbf758a596f0ea88727e/mako-1.3.12-py3-none-any.whl", hash = "sha256:8f61569480282dbf557145ce441e4ba888be453c30989f879f0d652e39f53ea9", size = 78521, upload-time = "2026-04-28T19:01:10.393Z" },
 ]
 
 [[package]]
@@ -3697,15 +3660,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/c7/18/c86eb8e0202e32dd3df50d43d7ff9854f8e0603945ff398974c1d91ac1ef/tomli_w-1.2.0-py3-none-any.whl", hash = "sha256:188306098d013b691fcadc011abd66727d3c414c571bb01b1a174ba8c983cf90", size = 6675, upload-time = "2025-01-15T12:07:22.074Z" },
 ]
 
-[[package]]
-name = "tomlkit"
-version = "0.14.0"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/c3/af/14b24e41977adb296d6bd1fb59402cf7d60ce364f90c890bd2ec65c43b5a/tomlkit-0.14.0.tar.gz", hash = "sha256:cf00efca415dbd57575befb1f6634c4f42d2d87dbba376128adb42c121b87064", size = 187167, upload-time = "2026-01-13T01:14:53.304Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/b5/11/87d6d29fb5d237229d67973a6c9e06e048f01cf4994dee194ab0ea841814/tomlkit-0.14.0-py3-none-any.whl", hash = "sha256:592064ed85b40fa213469f81ac584f67a4f2992509a7c3ea2d632208623a3680", size = 39310, upload-time = "2026-01-13T01:14:51.965Z" },
-]
-
 [[package]]
 name = "torch"
 version = "2.9.1"
@@ -3800,6 +3754,11 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/5d/95/0b0218149b0d6f14df35f5b8f676fa83df4f19ed253c3cc447107ef86eca/transformers-5.6.2-py3-none-any.whl", hash = "sha256:f8d3a1bb96778fed9b8aabfd0dd6e19843e4b0f2bb6b59f32b8a92051b0f348f", size = 10364898, upload-time = "2026-04-23T18:33:26.081Z" },
 ]
 
+[package.optional-dependencies]
+kernels = [
+    { name = "kernels" },
+]
+
 [[package]]
 name = "triton"
 version = "3.5.1"
@@ -3905,11 +3864,11 @@ wheels = [
 
 [[package]]
 name = "urllib3"
-version = "2.6.3"
+version = "2.7.0"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/c7/24/5f1b3bdffd70275f6661c76461e25f024d5a38a46f04aaca912426a2b1d3/urllib3-2.6.3.tar.gz", hash = "sha256:1b62b6884944a57dbe321509ab94fd4d3b307075e0c2eae991ac71ee15ad38ed", size = 435556, upload-time = "2026-01-07T16:24:43.925Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/53/0c/06f8b233b8fd13b9e5ee11424ef85419ba0d8ba0b3138bf360be2ff56953/urllib3-2.7.0.tar.gz", hash = "sha256:231e0ec3b63ceb14667c67be60f2f2c40a518cb38b03af60abc813da26505f4c", size = 433602, upload-time = "2026-05-07T16:13:18.596Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/39/08/aaaad47bc4e9dc8c725e68f9d04865dbcb2052843ff09c97b08904852d84/urllib3-2.6.3-py3-none-any.whl", hash = "sha256:bf272323e553dfb2e87d9bfd225ca7b0f467b919d7bbd355436d3fd37cb0acd4", size = 131584, upload-time = "2026-01-07T16:24:42.685Z" },
+    { url = "https://files.pythonhosted.org/packages/7f/3e/5db95bcf282c52709639744ca2a8b149baccf648e39c8cc87553df9eae0c/urllib3-2.7.0-py3-none-any.whl", hash = "sha256:9fb4c81ebbb1ce9531cce37674bbc6f1360472bc18ca9a553ede278ef7276897", size = 131087, upload-time = "2026-05-07T16:13:17.151Z" },
 ]
 
 [[package]]