Ty_Tech/heretic
4
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
130 Commits 1 Branch 4 Tags
7ebd92dfa757d936c15754e276fc9272c47f41b7
Commit Graph

24 Commits

Author SHA1 Message Date
dependabot[bot] 7ebd92dfa7 build(deps): bump pygments from 2.19.2 to 2.20.0 (#271) 
Bumps [pygments](https://github.com/pygments/pygments) from 2.19.2 to 2.20.0.
- [Release notes](https://github.com/pygments/pygments/releases)
- [Changelog](https://github.com/pygments/pygments/blob/master/CHANGES)
- [Commits](https://github.com/pygments/pygments/compare/2.19.2...2.20.0)

---
updated-dependencies:
- dependency-name: pygments
  dependency-version: 2.20.0
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2026-04-04 08:24:56 +05:30
dependabot[bot] 655d66ef24 build(deps): bump nltk from 3.9.3 to 3.9.4 (#270) 
Bumps [nltk](https://github.com/nltk/nltk) from 3.9.3 to 3.9.4.
- [Changelog](https://github.com/nltk/nltk/blob/develop/ChangeLog)
- [Commits](https://github.com/nltk/nltk/compare/3.9.3...3.9.4)

---
updated-dependencies:
- dependency-name: nltk
  dependency-version: 3.9.4
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2026-04-04 08:24:29 +05:30
dependabot[bot] 0f99c882ec build(deps): bump filelock from 3.20.0 to 3.20.3 (#269) 
Bumps [filelock](https://github.com/tox-dev/py-filelock) from 3.20.0 to 3.20.3.
- [Release notes](https://github.com/tox-dev/py-filelock/releases)
- [Changelog](https://github.com/tox-dev/filelock/blob/main/docs/changelog.rst)
- [Commits](https://github.com/tox-dev/py-filelock/compare/3.20.0...3.20.3)

---
updated-dependencies:
- dependency-name: filelock
  dependency-version: 3.20.3
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2026-04-04 08:23:59 +05:30
dependabot[bot] 92f851b693 build(deps): bump pillow from 12.0.0 to 12.1.1 (#268) 
Bumps [pillow](https://github.com/python-pillow/Pillow) from 12.0.0 to 12.1.1.
- [Release notes](https://github.com/python-pillow/Pillow/releases)
- [Changelog](https://github.com/python-pillow/Pillow/blob/main/CHANGES.rst)
- [Commits](https://github.com/python-pillow/Pillow/compare/12.0.0...12.1.1)

---
updated-dependencies:
- dependency-name: pillow
  dependency-version: 12.1.1
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2026-04-04 08:23:32 +05:30
dependabot[bot] 81e0c84ec6 build(deps): bump aiohttp from 3.13.2 to 3.13.4 (#267) 
---
updated-dependencies:
- dependency-name: aiohttp
  dependency-version: 3.13.4
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
 2026-04-04 08:10:51 +05:30
Philipp Emanuel Weidmann 96c7a7d98a fix: replace tqdm progress bars with Rich progress bars 2026-03-28 18:30:15 +05:30
Philipp Emanuel Weidmann 1126332281 feat: add integrated benchmarking system 2026-03-24 18:25:12 +05:30
Philipp Emanuel Weidmann 94775d4148 chore: update dependencies 2026-03-15 09:31:32 +05:30
Philipp Emanuel Weidmann 27097bfe8e build: bump version to 1.2.0 2026-02-14 18:11:42 +05:30
Philipp Emanuel Weidmann 6017bcd347 fix: use compatible release specifiers for non-dev dependencies 
Fixes #145

Credit to MuX on Discord for recognizing that this is an issue with Transformers 5
 2026-02-13 12:27:57 +05:30
Philipp Emanuel Weidmann 2690655a83 feat: print memory usage during run 2026-02-02 21:18:01 +05:30
anrp 85a6ec5ecb fix: Include kernels (allows MXFP4 to be loaded in MXFP4 instead of upcasting) (#107) 
Co-authored-by: Andrew Patrikalakis <anrp@tri.global>
 2026-01-16 17:30:24 +05:30
Philipp Emanuel Weidmann 39101137ef ci: add type checking 2025-12-22 10:48:42 +05:30
michaelh 243f821d93 feat: Add 4-bit loading + LoRA support for low VRAM optimization (#60) 
* 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>
 2025-12-14 20:19:09 +05:30
Philipp Emanuel Weidmann d9f2b0407a build: bump version to 1.1.0 2025-12-10 16:54:03 +05:30
Philipp Emanuel Weidmann 932d737edf feat: add silhouette coefficient to residual geometry output 2025-12-07 08:48:38 +05:30
Philipp Emanuel Weidmann baf5b0b0d1 feat: add geometric median to residual geometry output 2025-12-05 20:15:50 +05:30
Philipp Emanuel Weidmann eeb28b28c1 feat: add option to plot residual vectors 2025-12-04 14:22:29 +05:30
Philipp Emanuel Weidmann f06e939791 Add Ruff as a dev dependency 2025-11-19 09:59:18 +05:30
Philipp Emanuel Weidmann 3f346b6150 Change package name 2025-11-16 17:01:50 +05:30
Philipp Emanuel Weidmann ad8b04d371 Bump version to 1.0.0 2025-10-25 09:52:43 +05:30
Philipp Emanuel Weidmann dd7abd3296 Add hf_transfer to dependencies 
Required for repositories that don't use Xet
 2025-10-14 07:56:43 +05:30
Philipp Emanuel Weidmann 5b01ad4344 Add save and upload functionality 2025-09-27 11:15:41 +05:30
Philipp Emanuel Weidmann af19fbd254 Initial commit 2025-09-21 11:10:30 +05:30