mirror of
https://github.com/p-e-w/heretic.git
synced 2026-06-01 20:58:47 +02:00
michaelh
243f821d93
* Add files via upload * perf: optimize abliteration matrix op (#46) * perf: optimize abliteration matrix op * refactor: comments and var names correspond with arditi * refactor: fix comments and improve var notation * fix: accidental line change and improve comments --------- Co-authored-by: mad-cat-lon <113548315+mad-cat-lon@users.noreply.github.com> * Fix line endings to LF * Add hybrid approach for GPT-OSS compatibility - Check for LoRA adapters before attempting LoRA abliteration - Fall back to direct weight modification for nn.Parameter (GPT-OSS) - Ensures compatibility across all model architectures * Fix projector bug, update print statement, revert README * Revert README changes to match upstream * Fix import sorting for ruff * Fix reload_model for evaluate_model, add type hints and validation * Apply ruff formatting * Replace load_in_4bit with quantization enum * Fix precision loss: use FP32 refusal direction directly * Move r assignment into non-LoRA path * Fix linting: apply ruff formatting * Add auto-merge for LoRA adapters on save/upload * Fix linting: apply ruff formatting * Implement CPU-based merge for 4-bit models with OOM fallback * Remove use_lora flag (LoRA always on), add user prompt for 4-bit export * Fix: PEFT target_modules expects module names without path prefix * Fix linting: apply ruff formatting * Add LoRA fallback and fix quantization_config handling - Add try/except around LoRA initialization with fallback to direct weight modification - Only pass quantization_config when not None (fixes gpt-oss loading) - Use simple forward pass instead of generate() for model test (avoids chat template issues) - Reset non-LoRA models by reloading in reload_model() - Check self.use_lora before accessing LoRA adapters in abliterate() * Add 8-bit quantization support via bitsandbytes - Add BNB_8BIT option to QuantizationMethod enum - Add --load-in-8bit CLI support (auto via pydantic-settings) - Update documentation in config.py and config.default.toml - Useful for mid-range VRAM (12-16 GB) as balance between memory and numeric stability * Improve LoRA merge warning and fix linting * Apply final ruff formatting * Fix CI: apply ruff import sorting * Use tiny model for CI efficiency * Fix import sorting in test_lora.py * Fix formatting in test_lora.py * feat: Show merge warning for all models (requires high RAM) * style: Apply ruff fixes * Fix undefined Style import in main.py * Fix(model): Support MoE/3D tensors and enforce dtype safety in abliterate * Fix(ci): Format model.py with ruff * Fix(main): Remove invalid style argument from prompt_select and unused import * Fix logic errors, memory leak, and redundant merges in main.py * Fix linting and formatting issues (isort, ruff) * chore: Simplify .gitattributes as requested * refactor: Remove defensive try-except around LoRA initialization * chore: Update uv.lock with peft and bitsandbytes * chore: Regenerate uv.lock to include missing peft dependency * style: Fix import sorting (isort) for CI compliance * style: Simplify .gitattributes to single line as requested * Address PR #60 feedback: Remove caching, fix LoRA reload, global LoRA usage, style fixes * Address PR review comments: clarify code, fix quantization, rename method - Add explanatory comments for warning suppression and gc behavior - Remove redundant gc.collect() calls (empty_cache handles it) - Fix output message order (ask merge strategy before 'Uploading...') - Add comment explaining 8-bit quantization doesn't need compute_dtype - Remove extra newline after dtype comment - Add future-proofing note for hybrid layer support (#43) - Remove leftover comment in get_merged_model - Delete test_lora.py (debug script, not a real test) - Add comment explaining needs_reload flag purpose - Extract quantization config into _get_quantization_config() helper - Rename reload_model() to reset_model_for_trial() for clarity - Fix reload_model to respect quantization config (fixes evaluate_model bug) - Remove unused gc import * Restore gc.collect() before empty_cache() for large models * refactor: Remove LoRA fallback remnants, simplify code - Remove use_lora flag (always true since LoRA is always applied) - Remove isinstance(PeftModel) check in get_merged_model() (always true) - Simplify reset_model_for_trial() by removing defensive try/except - Remove redundant gc.collect() calls (empty_cache handles GC) - Remove unused gc import from main.py * Address p-e-w review feedback: rename reset_model, remove loaded_model_name, fix type hints, remove GPT-OSS MoE, update assertion * Restore skip logic for non-LoRA modules and fix 4-bit base_layer.weight access * Remove defensive lora_A check per review - get_layer_modules already filters * Fix try_add: nest component init inside Module check, add assert for unexpected types * Add note about module.weight assumption for type checking * Change 'Reloading model' to 'Resetting model' in logging --------- Co-authored-by: accemlcc <accemlcc@users.noreply.github.com> Co-authored-by: mad-cat-lon <113548315+mad-cat-lon@users.noreply.github.com> Co-authored-by: Hager <Michael.Hager@bruker.com>
69 lines
1.8 KiB
TOML
69 lines
1.8 KiB
TOML
[project]
|
|
name = "heretic-llm"
|
|
version = "1.1.0"
|
|
description = "Fully automatic censorship removal for language models"
|
|
readme = "README.md"
|
|
license = "AGPL-3.0-or-later"
|
|
authors = [
|
|
{ name = "Philipp Emanuel Weidmann", email = "pew@worldwidemann.com" }
|
|
]
|
|
requires-python = ">=3.10"
|
|
keywords = ["llm", "transformer", "abliteration"]
|
|
classifiers = [
|
|
"Development Status :: 4 - Beta",
|
|
"Environment :: Console",
|
|
"Environment :: GPU",
|
|
"Intended Audience :: Science/Research",
|
|
"License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)",
|
|
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
|
"Programming Language :: Python :: 3",
|
|
"Programming Language :: Python :: 3.10",
|
|
"Programming Language :: Python :: 3.11",
|
|
"Programming Language :: Python :: 3.12",
|
|
]
|
|
dependencies = [
|
|
"accelerate>=1.10.0",
|
|
"bitsandbytes>=0.45.0",
|
|
"datasets>=4.0.0",
|
|
"hf-transfer>=0.1.9",
|
|
"huggingface-hub>=0.34.4",
|
|
"optuna>=4.5.0",
|
|
"peft>=0.14.0",
|
|
"pydantic-settings>=2.10.1",
|
|
"questionary>=2.1.1",
|
|
"rich>=14.1.0",
|
|
"transformers>=4.55.2",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
research = [
|
|
"geom-median>=0.1.0",
|
|
"imageio>=2.37.2",
|
|
"matplotlib>=3.10.7",
|
|
"numpy>=2.2.6",
|
|
"pacmap>=0.8.0",
|
|
"scikit-learn>=1.7.2",
|
|
]
|
|
|
|
[dependency-groups]
|
|
dev = [
|
|
"ruff>=0.14.5",
|
|
]
|
|
|
|
[project.urls]
|
|
Homepage = "https://github.com/p-e-w/heretic"
|
|
Documentation = "https://github.com/p-e-w/heretic"
|
|
Repository = "https://github.com/p-e-w/heretic.git"
|
|
Issues = "https://github.com/p-e-w/heretic/issues"
|
|
Changelog = "https://github.com/p-e-w/heretic/releases"
|
|
|
|
[project.scripts]
|
|
heretic = "heretic.main:main"
|
|
|
|
[build-system]
|
|
requires = ["uv_build>=0.8.11,<0.9.0"]
|
|
build-backend = "uv_build"
|
|
|
|
[tool.uv.build-backend]
|
|
module-name = "heretic"
|