cjm-substrate-hf-utils 0.0.12__tar.gz

cjm_substrate_hf_utils-0.0.12/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2022, fastai
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

cjm_substrate_hf_utils-0.0.12/MANIFEST.in

@@ -0,0 +1,5 @@
+include pyproject.toml
+include LICENSE
+include CONTRIBUTING.md
+include README.md
+recursive-exclude * __pycache__

cjm_substrate_hf_utils-0.0.12/PKG-INFO

@@ -0,0 +1,169 @@
+Metadata-Version: 2.4
+Name: cjm-substrate-hf-utils
+Version: 0.0.12
+Summary: Hugging Face Hub helpers for cjm-substrate capabilities: cache-config mixin, progress-reporting snapshot downloads, and typed-OOM model loading.
+Author-email: "Christian J. Mills" <9126128+cj-mills@users.noreply.github.com>
+License: Apache-2.0
+Project-URL: Repository, https://github.com/cj-mills/cjm-substrate-hf-utils
+Project-URL: Documentation, https://cj-mills.github.io/cjm-substrate-hf-utils/
+Keywords: nbdev
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: cjm-substrate>=0.0.47
+Requires-Dist: cjm-substrate-torch-utils>=0.0.11
+Requires-Dist: huggingface_hub
+Requires-Dist: tqdm
+Dynamic: license-file
+
+# cjm-substrate-hf-utils
+
+
+<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->
+
+## Install
+
+``` bash
+pip install cjm_substrate_hf_utils
+```
+
+## Project Structure
+
+    nbs/
+    ├── cache_config.ipynb # A dataclass mixin adding HuggingFace Hub cache / revision / air-gap / security fields to a capability's config, with `RELOAD_TRIGGER` + JSON-schema metadata pre-set.
+    ├── download.ipynb     # Wrap `huggingface_hub.snapshot_download` so per-file progress flows to the capability's `report_progress`, defeating the substrate's stall detector during downloads.
+    └── loading.ipynb      # Call `model_class.from_pretrained(...)` and convert CUDA OOM into the substrate's typed `CapabilityResourceError` for CR-7 reactive retry.
+
+Total: 3 notebooks
+
+## Module Dependencies
+
+``` mermaid
+graph LR
+    cache_config["cache_config<br/>HF cache config mixin"]
+    download["download<br/>Snapshot download with progress"]
+    loading["loading<br/>Pretrained loading with typed OOM"]
+```
+
+No cross-module dependencies detected.
+
+## CLI Reference
+
+No CLI commands found in this project.
+
+## Module Overview
+
+Detailed documentation for each module in the project:
+
+### HF cache config mixin (`cache_config.ipynb`)
+
+> A dataclass mixin adding HuggingFace Hub cache / revision / air-gap /
+> security fields to a capability’s config, with `RELOAD_TRIGGER` +
+> JSON-schema metadata pre-set.
+
+#### Import
+
+``` python
+from cjm_substrate_hf_utils.cache_config import (
+    HFCacheConfig
+)
+```
+
+#### Classes
+
+``` python
+@dataclass
+class HFCacheConfig:
+    """
+    Mixin adding HuggingFace Hub cache/revision/air-gap/security fields to a capability config.
+    
+    Compose by inheritance:
+    
+        @dataclass
+        class MyCapabilityConfig(HFCacheConfig):
+            model_id: str = field(default="org/model", metadata={RELOAD_TRIGGER: "model"})
+            # ... capability-specific fields (all defaulted) ...
+    
+    Each field is `RELOAD_TRIGGER`-tagged `"model"` (a change invalidates a loaded
+    model) and carries `SCHEMA_TITLE`/`SCHEMA_DESC` so the capability-config UI renders
+    it. `trust_remote_code` defaults to False and is flagged DANGER in its help text.
+    """
+    
+    cache_dir: Optional[str] = field(...)
+    revision: Optional[str] = field(...)
+    local_files_only: bool = field(...)
+    trust_remote_code: bool = field(...)
+```
+
+### Snapshot download with progress (`download.ipynb`)
+
+> Wrap `huggingface_hub.snapshot_download` so per-file progress flows to
+> the capability’s `report_progress`, defeating the substrate’s stall
+> detector during downloads.
+
+#### Import
+
+``` python
+from cjm_substrate_hf_utils.download import (
+    snapshot_download_with_progress
+)
+```
+
+#### Functions
+
+``` python
+def snapshot_download_with_progress(
+    """
+    Download an HF Hub snapshot, streaming per-file progress to `report_progress`.
+    
+    When `report_progress` is given, a `tqdm_class` subclass forwards each update
+    as `report_progress(downloaded / total, "downloading <file>")`. When it is
+    None, the default HF Hub progress bars are used unchanged.
+    
+    Returns the local snapshot directory; subsequent `from_pretrained` calls with
+    the same `cache_dir` + `local_files_only=True` hit the populated cache.
+    
+    Adoption: the per-file tqdm callback is real progress but NOT a reliable
+    stall-detector floor on its own (it can be sparse / silent on one large file).
+    Wrap BOTH this call and the subsequent `from_pretrained` in a single
+    `with self.heartbeat(...)` block so the substrate always sees the tuple advance.
+    """
+```
+
+### Pretrained loading with typed OOM (`loading.ipynb`)
+
+> Call `model_class.from_pretrained(...)` and convert CUDA OOM into the
+> substrate’s typed `CapabilityResourceError` for CR-7 reactive retry.
+
+#### Import
+
+``` python
+from cjm_substrate_hf_utils.loading import (
+    load_pretrained_with_oom
+)
+```
+
+#### Functions
+
+``` python
+def load_pretrained_with_oom(
+    model_class: Type,            # A class exposing `.from_pretrained(repo_id, **kwargs)`
+    repo_id: str,                 # Model repo id or local path passed to from_pretrained
+    *,
+    label: Optional[str] = None,  # OOM-message context (default: f"loading {repo_id!r}")
+    **kwargs,                     # Forwarded verbatim to model_class.from_pretrained
+) -> Any:                         # The loaded model
+    """
+    Call `model_class.from_pretrained(repo_id, **kwargs)`, converting CUDA OOM to a typed error.
+    
+    On `torch.cuda.OutOfMemoryError`, re-raises as `CapabilityResourceError` (via
+    `cuda_oom_to_capability_resource_error`) so the substrate's CR-7 reactive-retry
+    path can evict + reload + retry. All other exceptions propagate unchanged.
+    
+    Wrap the call in `self.heartbeat(...)` at the capability site to cover the silent
+    construction phase; pre-download with `snapshot_download_with_progress` for
+    real download progress.
+    """
+```

cjm_substrate_hf_utils-0.0.12/README.md

@@ -0,0 +1,149 @@
+# cjm-substrate-hf-utils
+
+
+<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->
+
+## Install
+
+``` bash
+pip install cjm_substrate_hf_utils
+```
+
+## Project Structure
+
+    nbs/
+    ├── cache_config.ipynb # A dataclass mixin adding HuggingFace Hub cache / revision / air-gap / security fields to a capability's config, with `RELOAD_TRIGGER` + JSON-schema metadata pre-set.
+    ├── download.ipynb     # Wrap `huggingface_hub.snapshot_download` so per-file progress flows to the capability's `report_progress`, defeating the substrate's stall detector during downloads.
+    └── loading.ipynb      # Call `model_class.from_pretrained(...)` and convert CUDA OOM into the substrate's typed `CapabilityResourceError` for CR-7 reactive retry.
+
+Total: 3 notebooks
+
+## Module Dependencies
+
+``` mermaid
+graph LR
+    cache_config["cache_config<br/>HF cache config mixin"]
+    download["download<br/>Snapshot download with progress"]
+    loading["loading<br/>Pretrained loading with typed OOM"]
+```
+
+No cross-module dependencies detected.
+
+## CLI Reference
+
+No CLI commands found in this project.
+
+## Module Overview
+
+Detailed documentation for each module in the project:
+
+### HF cache config mixin (`cache_config.ipynb`)
+
+> A dataclass mixin adding HuggingFace Hub cache / revision / air-gap /
+> security fields to a capability’s config, with `RELOAD_TRIGGER` +
+> JSON-schema metadata pre-set.
+
+#### Import
+
+``` python
+from cjm_substrate_hf_utils.cache_config import (
+    HFCacheConfig
+)
+```
+
+#### Classes
+
+``` python
+@dataclass
+class HFCacheConfig:
+    """
+    Mixin adding HuggingFace Hub cache/revision/air-gap/security fields to a capability config.
+    
+    Compose by inheritance:
+    
+        @dataclass
+        class MyCapabilityConfig(HFCacheConfig):
+            model_id: str = field(default="org/model", metadata={RELOAD_TRIGGER: "model"})
+            # ... capability-specific fields (all defaulted) ...
+    
+    Each field is `RELOAD_TRIGGER`-tagged `"model"` (a change invalidates a loaded
+    model) and carries `SCHEMA_TITLE`/`SCHEMA_DESC` so the capability-config UI renders
+    it. `trust_remote_code` defaults to False and is flagged DANGER in its help text.
+    """
+    
+    cache_dir: Optional[str] = field(...)
+    revision: Optional[str] = field(...)
+    local_files_only: bool = field(...)
+    trust_remote_code: bool = field(...)
+```
+
+### Snapshot download with progress (`download.ipynb`)
+
+> Wrap `huggingface_hub.snapshot_download` so per-file progress flows to
+> the capability’s `report_progress`, defeating the substrate’s stall
+> detector during downloads.
+
+#### Import
+
+``` python
+from cjm_substrate_hf_utils.download import (
+    snapshot_download_with_progress
+)
+```
+
+#### Functions
+
+``` python
+def snapshot_download_with_progress(
+    """
+    Download an HF Hub snapshot, streaming per-file progress to `report_progress`.
+    
+    When `report_progress` is given, a `tqdm_class` subclass forwards each update
+    as `report_progress(downloaded / total, "downloading <file>")`. When it is
+    None, the default HF Hub progress bars are used unchanged.
+    
+    Returns the local snapshot directory; subsequent `from_pretrained` calls with
+    the same `cache_dir` + `local_files_only=True` hit the populated cache.
+    
+    Adoption: the per-file tqdm callback is real progress but NOT a reliable
+    stall-detector floor on its own (it can be sparse / silent on one large file).
+    Wrap BOTH this call and the subsequent `from_pretrained` in a single
+    `with self.heartbeat(...)` block so the substrate always sees the tuple advance.
+    """
+```
+
+### Pretrained loading with typed OOM (`loading.ipynb`)
+
+> Call `model_class.from_pretrained(...)` and convert CUDA OOM into the
+> substrate’s typed `CapabilityResourceError` for CR-7 reactive retry.
+
+#### Import
+
+``` python
+from cjm_substrate_hf_utils.loading import (
+    load_pretrained_with_oom
+)
+```
+
+#### Functions
+
+``` python
+def load_pretrained_with_oom(
+    model_class: Type,            # A class exposing `.from_pretrained(repo_id, **kwargs)`
+    repo_id: str,                 # Model repo id or local path passed to from_pretrained
+    *,
+    label: Optional[str] = None,  # OOM-message context (default: f"loading {repo_id!r}")
+    **kwargs,                     # Forwarded verbatim to model_class.from_pretrained
+) -> Any:                         # The loaded model
+    """
+    Call `model_class.from_pretrained(repo_id, **kwargs)`, converting CUDA OOM to a typed error.
+    
+    On `torch.cuda.OutOfMemoryError`, re-raises as `CapabilityResourceError` (via
+    `cuda_oom_to_capability_resource_error`) so the substrate's CR-7 reactive-retry
+    path can evict + reload + retry. All other exceptions propagate unchanged.
+    
+    Wrap the call in `self.heartbeat(...)` at the capability site to cover the silent
+    construction phase; pre-download with `snapshot_download_with_progress` for
+    real download progress.
+    """
+```

cjm_substrate_hf_utils-0.0.12/cjm_substrate_hf_utils/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.0.12"

cjm_substrate_hf_utils-0.0.12/cjm_substrate_hf_utils/_modidx.py

@@ -0,0 +1,13 @@
+# Autogenerated by nbdev
+
+d = { 'settings': { 'branch': 'main',
+                'doc_baseurl': '/cjm-substrate-hf-utils',
+                'doc_host': 'https://cj-mills.github.io',
+                'git_url': 'https://github.com/cj-mills/cjm-substrate-hf-utils',
+                'lib_path': 'cjm_substrate_hf_utils'},
+  'syms': { 'cjm_substrate_hf_utils.cache_config': { 'cjm_substrate_hf_utils.cache_config.HFCacheConfig': ( 'cache_config.html#hfcacheconfig',
+                                                                                                            'cjm_substrate_hf_utils/cache_config.py')},
+            'cjm_substrate_hf_utils.download': { 'cjm_substrate_hf_utils.download.snapshot_download_with_progress': ( 'download.html#snapshot_download_with_progress',
+                                                                                                                      'cjm_substrate_hf_utils/download.py')},
+            'cjm_substrate_hf_utils.loading': { 'cjm_substrate_hf_utils.loading.load_pretrained_with_oom': ( 'loading.html#load_pretrained_with_oom',
+                                                                                                             'cjm_substrate_hf_utils/loading.py')}}}

cjm_substrate_hf_utils-0.0.12/cjm_substrate_hf_utils/cache_config.py

@@ -0,0 +1,64 @@
+"""A dataclass mixin adding HuggingFace Hub cache / revision / air-gap / security fields to a capability's config, with `RELOAD_TRIGGER` + JSON-schema metadata pre-set.
+
+Docs: https://cj-mills.github.io/cjm-substrate-hf-utilscache_config.html.md"""
+
+# AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/cache_config.ipynb.
+
+# %% auto #0
+__all__ = ['HFCacheConfig']
+
+# %% ../nbs/cache_config.ipynb #exports
+from dataclasses import dataclass, field
+from typing import Optional
+
+from cjm_substrate.core.capability import RELOAD_TRIGGER
+from cjm_substrate.utils.validation import SCHEMA_TITLE, SCHEMA_DESC
+
+# %% ../nbs/cache_config.ipynb #hf-cache-config
+@dataclass
+class HFCacheConfig:
+    """Mixin adding HuggingFace Hub cache/revision/air-gap/security fields to a capability config.
+
+    Compose by inheritance:
+
+        @dataclass
+        class MyCapabilityConfig(HFCacheConfig):
+            model_id: str = field(default="org/model", metadata={RELOAD_TRIGGER: "model"})
+            # ... capability-specific fields (all defaulted) ...
+
+    Each field is `RELOAD_TRIGGER`-tagged `"model"` (a change invalidates a loaded
+    model) and carries `SCHEMA_TITLE`/`SCHEMA_DESC` so the capability-config UI renders
+    it. `trust_remote_code` defaults to False and is flagged DANGER in its help text.
+    """
+    cache_dir: Optional[str] = field(
+        default=None,
+        metadata={
+            RELOAD_TRIGGER: "model",
+            SCHEMA_TITLE: "HF Cache Directory",
+            SCHEMA_DESC: "Override the HF Hub cache location for model downloads (default: HF_HOME).",
+        },
+    )
+    revision: Optional[str] = field(
+        default=None,
+        metadata={
+            RELOAD_TRIGGER: "model",
+            SCHEMA_TITLE: "Model Revision",
+            SCHEMA_DESC: "Git revision / tag / commit to pin (default: the repo's main branch).",
+        },
+    )
+    local_files_only: bool = field(
+        default=False,
+        metadata={
+            RELOAD_TRIGGER: "model",
+            SCHEMA_TITLE: "Local Files Only",
+            SCHEMA_DESC: "Reject network access and use only cached files (air-gapped / reproducible).",
+        },
+    )
+    trust_remote_code: bool = field(
+        default=False,
+        metadata={
+            RELOAD_TRIGGER: "model",
+            SCHEMA_TITLE: "Trust Remote Code",
+            SCHEMA_DESC: "DANGER: allow execution of model-author code shipped in the repo.",
+        },
+    )

cjm_substrate_hf_utils-0.0.12/cjm_substrate_hf_utils/download.py

@@ -0,0 +1,56 @@
+"""Wrap `huggingface_hub.snapshot_download` so per-file progress flows to the capability's `report_progress`, defeating the substrate's stall detector during downloads.
+
+Docs: https://cj-mills.github.io/cjm-substrate-hf-utilsdownload.html.md"""
+
+# AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/download.ipynb.
+
+# %% auto #0
+__all__ = ['snapshot_download_with_progress']
+
+# %% ../nbs/download.ipynb #exports
+from pathlib import Path
+from typing import Callable, Optional
+
+from huggingface_hub import snapshot_download
+from tqdm.auto import tqdm as _tqdm
+
+# %% ../nbs/download.ipynb #snapshot-download
+def snapshot_download_with_progress(
+    repo_id: str,                                                    # HF Hub repo id, e.g. "mistralai/Voxtral-Mini-3B-2507"
+    *,
+    report_progress: Optional[Callable[[float, str], None]] = None,  # Capability's report_progress(fraction, message)
+    cache_dir: Optional[str] = None,                                 # HF cache override (HFCacheConfig.cache_dir)
+    revision: Optional[str] = None,                                  # Git rev / tag / commit to pin
+    local_files_only: bool = False,                                  # Use cached files only; no network
+    **kwargs,                                                        # Forwarded to huggingface_hub.snapshot_download
+) -> Path:                                                           # Local path to the downloaded snapshot
+    """Download an HF Hub snapshot, streaming per-file progress to `report_progress`.
+
+    When `report_progress` is given, a `tqdm_class` subclass forwards each update
+    as `report_progress(downloaded / total, "downloading <file>")`. When it is
+    None, the default HF Hub progress bars are used unchanged.
+
+    Returns the local snapshot directory; subsequent `from_pretrained` calls with
+    the same `cache_dir` + `local_files_only=True` hit the populated cache.
+
+    Adoption: the per-file tqdm callback is real progress but NOT a reliable
+    stall-detector floor on its own (it can be sparse / silent on one large file).
+    Wrap BOTH this call and the subsequent `from_pretrained` in a single
+    `with self.heartbeat(...)` block so the substrate always sees the tuple advance.
+    """
+    tqdm_class = None
+    if report_progress is not None:
+        class _ReportingTqdm(_tqdm):
+            def update(self, n=1):
+                super().update(n)
+                if self.total:
+                    report_progress(self.n / self.total, f"downloading {self.desc or repo_id}")
+        tqdm_class = _ReportingTqdm
+    return Path(snapshot_download(
+        repo_id,
+        cache_dir=cache_dir,
+        revision=revision,
+        local_files_only=local_files_only,
+        tqdm_class=tqdm_class,
+        **kwargs,
+    ))

cjm_substrate_hf_utils-0.0.12/cjm_substrate_hf_utils/loading.py

@@ -0,0 +1,40 @@
+"""Call `model_class.from_pretrained(...)` and convert CUDA OOM into the substrate's typed `CapabilityResourceError` for CR-7 reactive retry.
+
+Docs: https://cj-mills.github.io/cjm-substrate-hf-utilsloading.html.md"""
+
+# AUTOGENERATED! DO NOT EDIT! File to edit: ../nbs/loading.ipynb.
+
+# %% auto #0
+__all__ = ['load_pretrained_with_oom']
+
+# %% ../nbs/loading.ipynb #exports
+from typing import Any, Optional, Type
+
+import torch
+
+from cjm_substrate_torch_utils.oom import cuda_oom_to_capability_resource_error
+
+# %% ../nbs/loading.ipynb #load-pretrained
+def load_pretrained_with_oom(
+    model_class: Type,            # A class exposing `.from_pretrained(repo_id, **kwargs)`
+    repo_id: str,                 # Model repo id or local path passed to from_pretrained
+    *,
+    label: Optional[str] = None,  # OOM-message context (default: f"loading {repo_id!r}")
+    **kwargs,                     # Forwarded verbatim to model_class.from_pretrained
+) -> Any:                         # The loaded model
+    """Call `model_class.from_pretrained(repo_id, **kwargs)`, converting CUDA OOM to a typed error.
+
+    On `torch.cuda.OutOfMemoryError`, re-raises as `CapabilityResourceError` (via
+    `cuda_oom_to_capability_resource_error`) so the substrate's CR-7 reactive-retry
+    path can evict + reload + retry. All other exceptions propagate unchanged.
+
+    Wrap the call in `self.heartbeat(...)` at the capability site to cover the silent
+    construction phase; pre-download with `snapshot_download_with_progress` for
+    real download progress.
+    """
+    try:
+        return model_class.from_pretrained(repo_id, **kwargs)
+    except torch.cuda.OutOfMemoryError as e:
+        raise cuda_oom_to_capability_resource_error(
+            e, label=label or f"loading {repo_id!r}",
+        ) from e

cjm_substrate_hf_utils-0.0.12/cjm_substrate_hf_utils.egg-info/PKG-INFO

@@ -0,0 +1,169 @@
+Metadata-Version: 2.4
+Name: cjm-substrate-hf-utils
+Version: 0.0.12
+Summary: Hugging Face Hub helpers for cjm-substrate capabilities: cache-config mixin, progress-reporting snapshot downloads, and typed-OOM model loading.
+Author-email: "Christian J. Mills" <9126128+cj-mills@users.noreply.github.com>
+License: Apache-2.0
+Project-URL: Repository, https://github.com/cj-mills/cjm-substrate-hf-utils
+Project-URL: Documentation, https://cj-mills.github.io/cjm-substrate-hf-utils/
+Keywords: nbdev
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: cjm-substrate>=0.0.47
+Requires-Dist: cjm-substrate-torch-utils>=0.0.11
+Requires-Dist: huggingface_hub
+Requires-Dist: tqdm
+Dynamic: license-file
+
+# cjm-substrate-hf-utils
+
+
+<!-- WARNING: THIS FILE WAS AUTOGENERATED! DO NOT EDIT! -->
+
+## Install
+
+``` bash
+pip install cjm_substrate_hf_utils
+```
+
+## Project Structure
+
+    nbs/
+    ├── cache_config.ipynb # A dataclass mixin adding HuggingFace Hub cache / revision / air-gap / security fields to a capability's config, with `RELOAD_TRIGGER` + JSON-schema metadata pre-set.
+    ├── download.ipynb     # Wrap `huggingface_hub.snapshot_download` so per-file progress flows to the capability's `report_progress`, defeating the substrate's stall detector during downloads.
+    └── loading.ipynb      # Call `model_class.from_pretrained(...)` and convert CUDA OOM into the substrate's typed `CapabilityResourceError` for CR-7 reactive retry.
+
+Total: 3 notebooks
+
+## Module Dependencies
+
+``` mermaid
+graph LR
+    cache_config["cache_config<br/>HF cache config mixin"]
+    download["download<br/>Snapshot download with progress"]
+    loading["loading<br/>Pretrained loading with typed OOM"]
+```
+
+No cross-module dependencies detected.
+
+## CLI Reference
+
+No CLI commands found in this project.
+
+## Module Overview
+
+Detailed documentation for each module in the project:
+
+### HF cache config mixin (`cache_config.ipynb`)
+
+> A dataclass mixin adding HuggingFace Hub cache / revision / air-gap /
+> security fields to a capability’s config, with `RELOAD_TRIGGER` +
+> JSON-schema metadata pre-set.
+
+#### Import
+
+``` python
+from cjm_substrate_hf_utils.cache_config import (
+    HFCacheConfig
+)
+```
+
+#### Classes
+
+``` python
+@dataclass
+class HFCacheConfig:
+    """
+    Mixin adding HuggingFace Hub cache/revision/air-gap/security fields to a capability config.
+    
+    Compose by inheritance:
+    
+        @dataclass
+        class MyCapabilityConfig(HFCacheConfig):
+            model_id: str = field(default="org/model", metadata={RELOAD_TRIGGER: "model"})
+            # ... capability-specific fields (all defaulted) ...
+    
+    Each field is `RELOAD_TRIGGER`-tagged `"model"` (a change invalidates a loaded
+    model) and carries `SCHEMA_TITLE`/`SCHEMA_DESC` so the capability-config UI renders
+    it. `trust_remote_code` defaults to False and is flagged DANGER in its help text.
+    """
+    
+    cache_dir: Optional[str] = field(...)
+    revision: Optional[str] = field(...)
+    local_files_only: bool = field(...)
+    trust_remote_code: bool = field(...)
+```
+
+### Snapshot download with progress (`download.ipynb`)
+
+> Wrap `huggingface_hub.snapshot_download` so per-file progress flows to
+> the capability’s `report_progress`, defeating the substrate’s stall
+> detector during downloads.
+
+#### Import
+
+``` python
+from cjm_substrate_hf_utils.download import (
+    snapshot_download_with_progress
+)
+```
+
+#### Functions
+
+``` python
+def snapshot_download_with_progress(
+    """
+    Download an HF Hub snapshot, streaming per-file progress to `report_progress`.
+    
+    When `report_progress` is given, a `tqdm_class` subclass forwards each update
+    as `report_progress(downloaded / total, "downloading <file>")`. When it is
+    None, the default HF Hub progress bars are used unchanged.
+    
+    Returns the local snapshot directory; subsequent `from_pretrained` calls with
+    the same `cache_dir` + `local_files_only=True` hit the populated cache.
+    
+    Adoption: the per-file tqdm callback is real progress but NOT a reliable
+    stall-detector floor on its own (it can be sparse / silent on one large file).
+    Wrap BOTH this call and the subsequent `from_pretrained` in a single
+    `with self.heartbeat(...)` block so the substrate always sees the tuple advance.
+    """
+```
+
+### Pretrained loading with typed OOM (`loading.ipynb`)
+
+> Call `model_class.from_pretrained(...)` and convert CUDA OOM into the
+> substrate’s typed `CapabilityResourceError` for CR-7 reactive retry.
+
+#### Import
+
+``` python
+from cjm_substrate_hf_utils.loading import (
+    load_pretrained_with_oom
+)
+```
+
+#### Functions
+
+``` python
+def load_pretrained_with_oom(
+    model_class: Type,            # A class exposing `.from_pretrained(repo_id, **kwargs)`
+    repo_id: str,                 # Model repo id or local path passed to from_pretrained
+    *,
+    label: Optional[str] = None,  # OOM-message context (default: f"loading {repo_id!r}")
+    **kwargs,                     # Forwarded verbatim to model_class.from_pretrained
+) -> Any:                         # The loaded model
+    """
+    Call `model_class.from_pretrained(repo_id, **kwargs)`, converting CUDA OOM to a typed error.
+    
+    On `torch.cuda.OutOfMemoryError`, re-raises as `CapabilityResourceError` (via
+    `cuda_oom_to_capability_resource_error`) so the substrate's CR-7 reactive-retry
+    path can evict + reload + retry. All other exceptions propagate unchanged.
+    
+    Wrap the call in `self.heartbeat(...)` at the capability site to cover the silent
+    construction phase; pre-download with `snapshot_download_with_progress` for
+    real download progress.
+    """
+```

cjm_substrate_hf_utils-0.0.12/cjm_substrate_hf_utils.egg-info/SOURCES.txt

@@ -0,0 +1,15 @@
+LICENSE
+MANIFEST.in
+README.md
+pyproject.toml
+cjm_substrate_hf_utils/__init__.py
+cjm_substrate_hf_utils/_modidx.py
+cjm_substrate_hf_utils/cache_config.py
+cjm_substrate_hf_utils/download.py
+cjm_substrate_hf_utils/loading.py
+cjm_substrate_hf_utils.egg-info/PKG-INFO
+cjm_substrate_hf_utils.egg-info/SOURCES.txt
+cjm_substrate_hf_utils.egg-info/dependency_links.txt
+cjm_substrate_hf_utils.egg-info/entry_points.txt
+cjm_substrate_hf_utils.egg-info/requires.txt
+cjm_substrate_hf_utils.egg-info/top_level.txt

cjm_substrate_hf_utils-0.0.12/cjm_substrate_hf_utils.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

cjm_substrate_hf_utils-0.0.12/cjm_substrate_hf_utils.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[nbdev]
+cjm_substrate_hf_utils = cjm_substrate_hf_utils._modidx:d

cjm_substrate_hf_utils-0.0.12/cjm_substrate_hf_utils.egg-info/requires.txt

@@ -0,0 +1,4 @@
+cjm-substrate>=0.0.47
+cjm-substrate-torch-utils>=0.0.11
+huggingface_hub
+tqdm

cjm_substrate_hf_utils-0.0.12/cjm_substrate_hf_utils.egg-info/top_level.txt

@@ -0,0 +1 @@
+cjm_substrate_hf_utils

cjm_substrate_hf_utils-0.0.12/pyproject.toml

@@ -0,0 +1,33 @@
+[build-system]
+requires = ["setuptools>=64"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "cjm-substrate-hf-utils"
+dynamic = ["version"]
+description = "Hugging Face Hub helpers for cjm-substrate capabilities: cache-config mixin, progress-reporting snapshot downloads, and typed-OOM model loading."
+readme = "README.md"
+requires-python = ">=3.12"
+license = {text = "Apache-2.0"}
+authors = [{name = "Christian J. Mills", email = "9126128+cj-mills@users.noreply.github.com"}]
+keywords = ['nbdev']
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3 :: Only",
+]
+dependencies = ['cjm-substrate>=0.0.47', 'cjm-substrate-torch-utils>=0.0.11', 'huggingface_hub', 'tqdm']
+
+[project.urls]
+Repository = "https://github.com/cj-mills/cjm-substrate-hf-utils"
+Documentation = "https://cj-mills.github.io/cjm-substrate-hf-utils/"
+
+[project.entry-points.nbdev]
+cjm_substrate_hf_utils = "cjm_substrate_hf_utils._modidx:d"
+
+[tool.setuptools.dynamic]
+version = {attr = "cjm_substrate_hf_utils.__version__"}
+
+[tool.setuptools.packages.find]
+include = ["cjm_substrate_hf_utils"]
+
+[tool.nbdev]

cjm_substrate_hf_utils-0.0.12/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+