mirror of
https://github.com/wassname/steer-heal-love.git
synced 2026-06-27 17:02:34 +08:00
qlora+bs=4 batched heal, walk-C bisection, round-loosened barrier
- QLoRA (4-bit NF4) base frees ~6GB -> train_bs=4 + grad_accum=4 (block/Linear-level hooks survive bnb Linear4bit: add to dequantized output, same pattern as peft randlora/bnb.py) - walk-C: log-kappa bisection dose controller, ~5 probes of 8 gens to highest kappa with >=75% filter survival, then collect to n_keep - filter: char-level n-gram rep (catches TTTT/!!!! loops), ppl over the tail 25% of completion (steering collapses mid-completion) - lam_round_pow<0 loosens the KL-to-base barrier with round (lam_eff=lam/sqrt(1+N)): only the cumulative-vs-fixed-anchor barrier self-inflates with round; per-increment spectral_lam + weight_decay stay flat - alphas capped at 1.0, gen_pass_target 0.75 Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
This commit is contained in:
@@ -11,7 +11,7 @@ resolution-markers = [
|
||||
]
|
||||
|
||||
[options]
|
||||
exclude-newer = "2026-05-30T09:16:42.439409688Z"
|
||||
exclude-newer = "2026-06-04T01:47:06.189839469Z"
|
||||
exclude-newer-span = "P5D"
|
||||
|
||||
[[package]]
|
||||
@@ -215,6 +215,22 @@ wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/71/cc/18245721fa7747065ab478316c7fea7c74777d07f37ae60db2e84f8172e8/beartype-0.22.9-py3-none-any.whl", hash = "sha256:d16c9bbc61ea14637596c5f6fbff2ee99cbe3573e46a716401734ef50c3060c2", size = 1333658, upload-time = "2025-12-13T06:50:28.266Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "bitsandbytes"
|
||||
version = "0.49.2"
|
||||
source = { registry = "https://pypi.org/simple" }
|
||||
dependencies = [
|
||||
{ name = "numpy" },
|
||||
{ name = "packaging" },
|
||||
{ name = "torch" },
|
||||
]
|
||||
wheels = [
|
||||
{ url = "https://files.pythonhosted.org/packages/d8/7d/f1fe0992334b18cd8494f89aeec1dcc674635584fcd9f115784fea3a1d05/bitsandbytes-0.49.2-py3-none-macosx_14_0_arm64.whl", hash = "sha256:87be5975edeac5396d699ecbc39dfc47cf2c026daaf2d5852a94368611a6823f", size = 131940, upload-time = "2026-02-16T21:26:04.572Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/29/71/acff7af06c818664aa87ff73e17a52c7788ad746b72aea09d3cb8e424348/bitsandbytes-0.49.2-py3-none-manylinux_2_24_aarch64.whl", hash = "sha256:2fc0830c5f7169be36e60e11f2be067c8f812dfcb829801a8703735842450750", size = 31442815, upload-time = "2026-02-16T21:26:06.783Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/19/57/3443d6f183436fbdaf5000aac332c4d5ddb056665d459244a5608e98ae92/bitsandbytes-0.49.2-py3-none-manylinux_2_24_x86_64.whl", hash = "sha256:54b771f06e1a3c73af5c7f16ccf0fc23a846052813d4b008d10cb6e017dd1c8c", size = 60651714, upload-time = "2026-02-16T21:26:11.579Z" },
|
||||
{ url = "https://files.pythonhosted.org/packages/b6/d4/501655842ad6771fb077f576d78cbedb5445d15b1c3c91343ed58ca46f0e/bitsandbytes-0.49.2-py3-none-win_amd64.whl", hash = "sha256:2e0ddd09cd778155388023cbe81f00afbb7c000c214caef3ce83386e7144df7d", size = 55372289, upload-time = "2026-02-16T21:26:16.267Z" },
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "catalogue"
|
||||
version = "2.0.10"
|
||||
@@ -2454,6 +2470,7 @@ dependencies = [
|
||||
{ name = "accelerate" },
|
||||
{ name = "baukit" },
|
||||
{ name = "beartype" },
|
||||
{ name = "bitsandbytes" },
|
||||
{ name = "datasets" },
|
||||
{ name = "einops" },
|
||||
{ name = "iso-kl-figure" },
|
||||
@@ -2480,6 +2497,7 @@ requires-dist = [
|
||||
{ name = "accelerate" },
|
||||
{ name = "baukit", git = "https://github.com/davidbau/baukit.git" },
|
||||
{ name = "beartype" },
|
||||
{ name = "bitsandbytes", specifier = ">=0.49.2" },
|
||||
{ name = "datasets" },
|
||||
{ name = "einops" },
|
||||
{ name = "iso-kl-figure", editable = "docs/vendor/isokl_steering_calibration" },
|
||||
|
||||
Reference in New Issue
Block a user