lora-lite/docs/audit/variants_review.md

[client] initialize (running)

[client] session/new (running) I’ll use the gsd skill because this is a multi-step audit, then I’ll read the variant code, paper excerpts, logs, and refs only as needed. No code edits, just a verdict with quoted evidence.

[tool] Read SKILL.md (running) input: {"call_id":"call_ZJ8jUrIxVXwLtDtWUHoN5Nyw","process_id":"8344","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","sed -n '1,220p' /home/wassname/.claude/skills/gsd/SKILL.md"],"cwd":"/med... files: /home/wassname/.claude/skills/gsd/SKILL.md

[tool] Read SKILL.md (completed) kind: read input: {"call_id":"call_ZJ8jUrIxVXwLtDtWUHoN5Nyw","process_id":"8344","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","sed -n '1,220p' /home/wassname/.claude/skills/gsd/SKILL.md"],"cwd":"/med... files: /home/wassname/.claude/skills/gsd/SKILL.md output: sed: /tmp/.mount_vscodiOHg5sd/lib/x86_64-linux-gnu/libselinux.so.1: no version information available (required by sed) --- name: gsd description: "Get Shit Done workflow for non-trivial tasks: spec -> implement -> test -> review -> wrap. Mandatory for anything with more than one step." ---

<!--
Design rationale and sources — for human readers, not the agent.

- GSD spec-first: spec-driven development, scope fencing, verify-before-done
- Manus file-as-memory: one file is working memory, checklist is state, append-only log
- Boomerang: return concrete artifacts not summaries
- DCP: invisible dedup, superseded writes, error purging

Core principles:
- Spec file is the only persistent artifact (single-file invariant).
- Agent shouldn't know about its own resource limits.
- Review scales with input size: frontier for plans, cheap for bulk.
- Observable outputs: show evidence, not narration.
-->

# GSD (Get Shit Done)

Mandatory for all non-trivial tasks (more than one step). Skip only for single-line fixes.

## Part 1: Core workflow

### 1.1 Spec-first planning
... (192 more lines)

I’m treating the GSD “spec” as an in-memory checklist here because your request explicitly says no edits and the filesystem is read-only. I’m going to gather hard evidence first: line-numbered code, paper anchors, logs, and any reference snippets that resolve ambiguity.

[tool] List /media/wassname/SGIronWolf/projects5/2026/lora-lite/lora_lite (running) input: {"call_id":"call_LrMg9wIgw4ohnwkqUAtJRrss","process_id":"31422","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","rg --files src/lora_lite docs/papers docs/refs logs"],"cwd":"/media/was... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/lora_lite

[tool] Read smoke.log (running) input: {"call_id":"call_UGl5ewNsDGBeS2Dhqvjea8gK","process_id":"66572","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","sed -n '1,240p' logs/smoke.log"],"cwd":"/media/wassname/SGIronWolf/proj... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/logs/smoke.log

[tool] Read qwen_probe.log (running) input: {"call_id":"call_NVGdpn8BCjAn1aXHyrZGHVGE","process_id":"83314","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","sed -n '1,240p' logs/qwen_probe.log"],"cwd":"/media/wassname/SGIronWolf... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/logs/qwen_probe.log

[tool] List /media/wassname/SGIronWolf/projects5/2026/lora-lite/lora_lite (completed) kind: search input: {"call_id":"call_LrMg9wIgw4ohnwkqUAtJRrss","process_id":"31422","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","rg --files src/lora_lite docs/papers docs/refs logs"],"cwd":"/media/was... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/lora_lite output: docs/refs/peft_eva_finetuning.py src/lora_lite/target.py docs/refs/antipasto3_svd_adapter.py docs/refs/peft_eva.py docs/refs/baukit_nethook.py src/lora_lite/__init__.py src/lora_lite/variant.py src/lora_lite/config.py src/lora_lite/adapter.py src/lora_lite/variants/pissa.py src/lora_lite/variants/ia3.py src/lora_lite/variants/lora.py src/lora_lite/variants/dora.py src/lora_lite/variants/delora.py src/lora_lite/variants/__init__.py src/lora_lite/variants/hra.py

[tool] Read qwen_probe.log (completed) kind: read input: {"call_id":"call_NVGdpn8BCjAn1aXHyrZGHVGE","process_id":"83314","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","sed -n '1,240p' logs/qwen_probe.log"],"cwd":"/media/wassname/SGIronWolf... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/logs/qwen_probe.log output: sed: /tmp/.mount_vscodiOHg5sd/lib/x86_64-linux-gnu/libselinux.so.1: no version information available (required by sed) New task added (id 84). SHOULD: exact q_proj/v_proj layer-0 targets, lora-only grads, lossN<loss0, perturb>0, reload<tol. ELSE hook/target/train/save bug.

Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 11183.76it/s]

Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 10483.91it/s]

Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 11231.62it/s]

Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 11419.02it/s]

Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 11501.48it/s]

Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 10138.41it/s]

Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 11177.81it/s]

Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 10532.84it/s]

Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 10290.29it/s]

Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 11146.68it/s]

Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 10274.97it/s]

Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 10701.60it/s] variant targets trainable id_err perturb loss0 lossN drop% grad dθ reload out lora 2 20480 0 0.2969 5.25 2.509 52.22 1.349 5....

[tool] Read smoke.log (completed) kind: read input: {"call_id":"call_UGl5ewNsDGBeS2Dhqvjea8gK","process_id":"66572","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","sed -n '1,240p' logs/smoke.log"],"cwd":"/media/wassname/SGIronWolf/proj... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/logs/smoke.log output: sed: /tmp/.mount_vscodiOHg5sd/lib/x86_64-linux-gnu/libselinux.so.1: no version information available (required by sed) /media/wassname/SGIronWolf/projects5/2026/lora-lite/.venv/lib/python3.13/site-packages/bitsandbytes/autograd/_functions.py:123: UserWarning: MatMul8bitLt: inputs will be cast from torch.float32 to float16 during quantization warnings.warn(f"MatMul8bitLt: inputs will be cast from {A.dtype} to float16 during quantization") /media/wassname/SGIronWolf/projects5/2026/lora-lite/.venv/lib/python3.13/site-packages/bitsandbytes/backends/cuda/ops.py:213: FutureWarning: _check_is_size will be removed in a future PyTorch release along with guard_size_oblivious. Use _check(i >= 0) instead. torch._check_is_size(blocksize)

=== variant=lora dtype=torch.float32 ===
  attached 28 targets, trainable params=17408
  t=0 identity: max|y_adapt - y_base| = 0.000e+00  (base scale 4.609e+00)
  SHOULD: err<4.6e-06. PASS.
  save/load: max|y_loaded - y_adapt| = 0.000e+00
  SHOULD: err2<4.6e-06. PASS.
  loss[0]=1.0882  loss[-1]=1.0220  drop=6.1%
  SHOULD: drop>5%. PASS.

=== variant=pissa dtype=torch.float32 ===
  attached 28 targets, trainable params=17408
  t=0 identity: max|y_adapt - y_base| = 1.550e-06  (base scale 4.609e+00)
  SHOULD: err<2.3e-03. PASS.
  save/load: max|y_loaded - y_adapt| = 0.000e+00
  SHOULD: err2<2.3e-03. PASS.
  loss[0]=1.0823  loss[-1]=0.9583  drop=11.5%
  SHOULD: drop>5%. PASS.

=== variant=delora dtype=torch.float32 ===
  attached 28 targets, trainable params=17436
  t=0 identity: max|y_adapt - y_base| = 0.000e+00  (base scale 4.609e+00)
  SHOULD: err<4.6e-06. PASS.
... (54 more lines)

[tool] Read pissa.py (running) input: {"call_id":"call_PHAInlKqf4e79zhlDJiBvHfL","process_id":"17726","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","nl -ba src/lora_lite/variants/pissa.py"],"cwd":"/media/wassname/SGIronW... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/src/lora_lite/variants/pissa.py

[tool] Read lora.py (running) input: {"call_id":"call_wgFgKkJ4EWh2naGB2Dxzmxeq","process_id":"53887","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","nl -ba src/lora_lite/variants/lora.py"],"cwd":"/media/wassname/SGIronWo... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/src/lora_lite/variants/lora.py

[tool] Read lora.py (completed) kind: read input: {"call_id":"call_wgFgKkJ4EWh2naGB2Dxzmxeq","process_id":"53887","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","nl -ba src/lora_lite/variants/lora.py"],"cwd":"/media/wassname/SGIronWo... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/src/lora_lite/variants/lora.py output: 1 """Vanilla LoRA. Hu et al. 2021 https://arxiv.org/abs/2106.09685 2 3 h = W x + (alpha/r) B A x 4 5 Identity at t=0 from B=0. Faithful to the paper. 6 """ 7 from einops import einsum 8 from torch import nn 9 import torch 10 11 from ..variant import register, ParamSpec 12 13 14 @register 15 class LoRA: 16 name = "lora" 17 18 @staticmethod 19 def param_specs(d_in, d_out, cfg): 20 return { 21 "lora_A": ParamSpec((cfg.r, d_in), init="kaiming", trainable=True), 22 "lora_B": ParamSpec((d_out, cfg.r), init="zeros", trainable=True), 23 } 24 25 @staticmethod 26 def init(layer: nn.Linear, cfg) -> None: 27 # B is zeros => delta=0 at t=0; identity invariant holds. 28 return ... (8 more lines)

[tool] Read pissa.py (completed) kind: read input: {"call_id":"call_PHAInlKqf4e79zhlDJiBvHfL","process_id":"17726","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","nl -ba src/lora_lite/variants/pissa.py"],"cwd":"/media/wassname/SGIronW... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/src/lora_lite/variants/pissa.py output: 1 """PiSSA: top-r SVD of W into A,B; replace W with W_res = W - B@A. 2 3 Meng et al. 2024 https://arxiv.org/abs/2404.02948 4 W_eff(t=0) = W_res + B@A = W (numerically; bf16 round-trip not bit-exact). 5 """ 6 import torch 7 from einops import einsum 8 from torch import nn 9 10 from ..variant import register, ParamSpec 11 12 13 @register 14 class PiSSA: 15 name = "pissa" 16 17 @staticmethod 18 def param_specs(d_in, d_out, cfg): 19 return { 20 "lora_A": ParamSpec((cfg.r, d_in), init="zeros", trainable=True), 21 "lora_B": ParamSpec((d_out, cfg.r), init="zeros", trainable=True), 22 } 23 24 @staticmethod 25 def init(layer: nn.Linear, cfg) -> None: 26 if type(layer) is not nn.Linear: 27 raise TypeError( 28 "PiSSA mutates layer.weight into W_res, so v1 only supports plain nn.Linear. " ... (26 more lines)

[tool] Read ia3.py (running) input: {"call_id":"call_vTvRjbwmBsdDiIngobGbh5cB","process_id":"83902","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","nl -ba src/lora_lite/variants/ia3.py"],"cwd":"/media/wassname/SGIronWol... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/src/lora_lite/variants/ia3.py

[tool] Read dora.py (running) input: {"call_id":"call_Vw9lIGlnQoz5jeOy3IYrKUHS","process_id":"14313","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","nl -ba src/lora_lite/variants/dora.py"],"cwd":"/media/wassname/SGIronWo... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/src/lora_lite/variants/dora.py

[tool] Read ia3.py (completed) kind: read input: {"call_id":"call_vTvRjbwmBsdDiIngobGbh5cB","process_id":"83902","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","nl -ba src/lora_lite/variants/ia3.py"],"cwd":"/media/wassname/SGIronWol... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/src/lora_lite/variants/ia3.py output: 1 """IA3-style output gating. Liu et al. 2022 https://arxiv.org/abs/2205.05638 2 3 y_new = y * g, g initialized to 1 (identity at t=0) 4 5 DEVIATION FROM PAPER: 6 The original IA3 gates only three positions per transformer block: 7 l_k * (k_proj output), l_v * (v_proj output), l_ff * (FFN intermediate after activation) 8 This implementation gates ANY linear layer the targeting system selects. 9 To match the paper exactly on a typical Llama/Qwen-style block, attach with: 10 11 cfg = LoraLiteConfig( 12 variant="ia3", 13 target_names=(r"\.k_proj$", r"\.v_proj$", r"\.up_proj$"), 14 target_roles=(), 15 ) 16 17 up_proj is the closest stand-in for "FFN intermediate" in gated-MLP blocks 18 (Llama uses gate * up; gating the up branch is the IA3-spirit choice). 19 """ 20 import torch 21 from torch import nn 22 23 from ..variant import register, ParamSpec 24 25 26 @register 27 class IA3: 28 name = "ia3" ... (12 more lines)

[tool] Read dora.py (completed) kind: read input: {"call_id":"call_Vw9lIGlnQoz5jeOy3IYrKUHS","process_id":"14313","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","nl -ba src/lora_lite/variants/dora.py"],"cwd":"/media/wassname/SGIronWo... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/src/lora_lite/variants/dora.py output: 1 """DoRA: weight-decomposed LoRA. Liu et al. 2024 https://arxiv.org/abs/2402.09353 2 3 W' = m * V / ||V||_c where V = W + (alpha/r) B A (||.||_c = per-output-row L2 norm) 4 5 At t=0: B=0 -> V=W -> y_new = (m_init / ||W||_c) (Wx + 0) = Wx when m_init = ||W||_c. 6 7 Limitation: requires materializing the dense weight to compute ||V||_c. v1 supports 8 plain nn.Linear only; bnb 4/8-bit layers raise loudly. 9 """ 10 import torch 11 import torch.nn.functional as F 12 from einops import einsum 13 from torch import nn 14 15 from ..variant import register, ParamSpec 16 17 18 @register 19 class DoRA: 20 name = "dora" 21 22 @staticmethod 23 def param_specs(d_in, d_out, cfg): 24 return { 25 "lora_A": ParamSpec((cfg.r, d_in), init="kaiming", trainable=True), 26 "lora_B": ParamSpec((d_out, cfg.r), init="zeros", trainable=True), 27 # m is filled from ||W||_c during init(); shape (d_out,) 28 "lora_m": ParamSpec((d_out,), init="zeros", trainable=True), ... (27 more lines)

[tool] Read delora.py (running) input: {"call_id":"call_1QShJSCjExZn5oGZqc78uF7b","process_id":"51148","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","nl -ba src/lora_lite/variants/delora.py"],"cwd":"/media/wassname/SGIron... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/src/lora_lite/variants/delora.py

[tool] Read adapter.py (running) input: {"call_id":"call_QOJFiy0Ooh70IhQEnPLRA2tX","process_id":"61139","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","nl -ba src/lora_lite/adapter.py"],"cwd":"/media/wassname/SGIronWolf/pro... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/src/lora_lite/adapter.py

[tool] Read hra.py (running) input: {"call_id":"call_mXp2R9UAQaI8I95Mc8fZh0Fm","process_id":"29257","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","nl -ba src/lora_lite/variants/hra.py"],"cwd":"/media/wassname/SGIronWol... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/src/lora_lite/variants/hra.py

[tool] Read variant.py (running) input: {"call_id":"call_6XIUIUymL7F6gKF9QAvv5ljV","process_id":"69737","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","nl -ba src/lora_lite/variant.py"],"cwd":"/media/wassname/SGIronWolf/pro... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/src/lora_lite/variant.py

[tool] Read delora.py (completed) kind: read input: {"call_id":"call_1QShJSCjExZn5oGZqc78uF7b","process_id":"51148","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","nl -ba src/lora_lite/variants/delora.py"],"cwd":"/media/wassname/SGIron... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/src/lora_lite/variants/delora.py output: 1 """DeLoRA: column-normalised A, B, scaled by lambda * ||W||_F / r. 2 3 Bini et al. 2025 https://arxiv.org/abs/2503.18225 4 5 Paper Eq. 8: W' = W + (lambda * ||W||F / r) B Xi A 6 where Xi{i,i} = 1 / (||b_i|| ||a_i||) makes each rank-1 component unit-norm. 7 This is equivalent to row-normalising A and column-normalising B (each column of 8 B and row of A has unit norm), so each rank-1 outer product b_i a_i^T has unit 9 spectral norm -> the whole low-rank update is bounded. 10 11 Identity at t=0: paper uses kaiming init for both A and B with lambda initialised 12 to 0 (or small) so the effective delta starts near zero. We honour that: 13 default lambda0 == 0 gives bit-identity; user can override via variant_kwargs. 14 15 The frozen ||W||_F factor is captured once at init() into a buffer lora_wnorm. 16 """ 17 import torch 18 import torch.nn.functional as F 19 from einops import einsum 20 from torch import nn 21 22 from ..variant import register, ParamSpec 23 24 25 @register 26 class DeLoRA: 27 name = "delora" 28 ... (32 more lines)

[tool] Read adapter.py (completed) kind: read input: {"call_id":"call_QOJFiy0Ooh70IhQEnPLRA2tX","process_id":"61139","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","nl -ba src/lora_lite/adapter.py"],"cwd":"/media/wassname/SGIronWolf/pro... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/src/lora_lite/adapter.py output: 1 """attach / detach / save / load. The whole runtime.""" 2 from future import annotations 3 import torch 4 from torch import nn 5 from torch.utils.hooks import RemovableHandle 6 7 from .config import LoraLiteConfig 8 from .variant import REGISTRY 9 from .target import find_targets 10 11 12 _ATTACHED_ATTR = "_lora_lite_attached" 13 14 15 def _hook(layer, args, y): 16 (x,) = args 17 cfg: LoraLiteConfig = layer._lora_cfg 18 x_cast = x.to(cfg.dtype) 19 out = layer._lora_variant.forward(layer, x_cast, y) 20 return out.to(y.dtype) 21 22 23 def _pre_hook(layer, args): 24 (x,) = args 25 cfg: LoraLiteConfig = layer._lora_cfg 26 x_cast = x.to(cfg.dtype) 27 x_new = layer._lora_variant.forward_input(layer, x_cast) 28 return (x_new.to(x.dtype),) ... (86 more lines)

[tool] Read hra.py (completed) kind: read input: {"call_id":"call_mXp2R9UAQaI8I95Mc8fZh0Fm","process_id":"29257","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","nl -ba src/lora_lite/variants/hra.py"],"cwd":"/media/wassname/SGIronWol... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/src/lora_lite/variants/hra.py output: 1 """HRA: Householder Reflection Adaptation. Yuan et al. 2024 https://arxiv.org/abs/2405.17484 2 3 Paper formulation (Sec. 3): adapt each frozen weight as 4 5 W' = W R, R = prod_{i=1..r} H_i, H_i = I - 2 u_i u_i^T / ||u_i||^2 6 7 so the layer output becomes y' = W' x = W (R x). R is in INPUT space (d_in x d_in). 8 9 We implement this via a forward_input pre-hook that returns R x, then the 10 frozen base layer (including bnb 4/8-bit Linear) computes W (R x) itself. 11 12 Identity at t=0: lora_gate is initialized to 0 and gates each Householder 13 vector, so the effective u_i starts at 0 -> H_i = I -> R = I -> y' = y. 14 At training time the gate scales the active reflection direction. 15 16 OMITTED: paper also adds an orthogonality regularizer 17 lambda * sum_i (u_i^T u_j)^2 (Eq. 6 / Sec. 3.3) 18 which is a loss term, not a forward-pass change. Add it in your training loop if 19 you want the regularized HRA variant. 20 """ 21 import torch 22 from einops import einsum 23 from torch import nn 24 25 from ..variant import register, ParamSpec 26 27 28 @register ... (27 more lines)

[tool] Read variant.py (completed) kind: read input: {"call_id":"call_6XIUIUymL7F6gKF9QAvv5ljV","process_id":"69737","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","nl -ba src/lora_lite/variant.py"],"cwd":"/media/wassname/SGIronWolf/pro... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/src/lora_lite/variant.py output: 1 """Variant protocol + registry. Variants own (x, layer.weight, layer.lora_*) -> y_new.""" 2 from dataclasses import dataclass 3 from typing import Callable, Protocol, Any 4 import torch 5 from torch import nn 6 7 from .config import LoraLiteConfig 8 9 10 @dataclass 11 class ParamSpec: 12 shape: tuple[int, ...] 13 init: str | Callable[[torch.Tensor], None] = "zeros" # 'zeros'|'kaiming'|'ones'|callable(t) 14 trainable: bool = True 15 16 def make(self, dtype: torch.dtype, device) -> nn.Parameter: 17 t = torch.empty(self.shape, dtype=dtype, device=device) 18 if callable(self.init): 19 self.init(t) 20 elif self.init == "zeros": 21 t.zero_() 22 elif self.init == "ones": 23 t.fill_(1.0) 24 elif self.init == "kaiming": 25 # match nn.Linear default: kaiming_uniform_(a=sqrt(5)) 26 nn.init.kaiming_uniform_(t, a=5 ** 0.5) if t.ndim >= 2 else t.normal_(0, 0.02) 27 else: 28 raise ValueError(f"unknown init: {self.init}") ... (28 more lines) The code already shows several documented deviations, so I’m checking those against the extracted papers rather than relying on the docstrings. Next I’m pulling section/equation anchors from the paper text and logs with line numbers so the review can be evidence-heavy.

[tool] Search PiSSA|SVD|singular|residual|A =|B =|W_res|Eq|equation|principal|initialize|initial in pissa_*.txt (running) input: {"call_id":"call_E9ZDiQW4LYUvXfsbLERUR8VE","process_id":"40256","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","rg -n "PiSSA|SVD|singular|residual|A =|B =|W_res|Eq|equation|principal...

[tool] Search IA3|l_k|l_v|l_ff|key|value|feed-forward|activation|element-wise|Eq|equation|rescale|learned vector in ia3_*.txt (running) input: {"call_id":"call_g8eWpsF9Wv2q0sr9uIOTKAXt","process_id":"6527","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","rg -n "IA3|l_k|l_v|l_ff|key|value|feed-forward|activation|element-wise|...

[tool] Search LoRA|low-rank|A|B|alpha|rank|Eq|equation|ΔW|Delta|zero|Gaussian|Kaiming|initial in lora_*.txt (running) input: {"call_id":"call_bWnP0o9dE2sMNEN6N5a9w6Jp","process_id":"2585","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","rg -n "LoRA|low-rank|A|B|alpha|rank|Eq|equation|ΔW|Delta|zero|Gaussian|...

[tool] Search DoRA|magnitude|direction|decompose|norm|V =|Eq|equation|initialize|column|row in dora_*.txt (running) input: {"call_id":"call_u0hqS6Uap4DQRdjRTfjZS35I","process_id":"15602","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","rg -n "DoRA|magnitude|direction|decompose|norm|V =|Eq|equation|initial...

[tool] Search PiSSA|SVD|singular|residual|A =|B =|W_res|Eq|equation|principal|initialize|initial in pissa_*.txt (completed) kind: search input: {"call_id":"call_E9ZDiQW4LYUvXfsbLERUR8VE","process_id":"40256","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","rg -n "PiSSA|SVD|singular|residual|A =|B =|W_res|Eq|equation|principal... output: binary file matches (found "\0" byte around offset 4333)

[tool] Search IA3|l_k|l_v|l_ff|key|value|feed-forward|activation|element-wise|Eq|equation|rescale|learned vector in ia3_*.txt (completed) kind: search input: {"call_id":"call_g8eWpsF9Wv2q0sr9uIOTKAXt","process_id":"6527","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","rg -n "IA3|l_k|l_v|l_ff|key|value|feed-forward|activation|element-wise|... output: 19:method called (IA)3 that scales activations by learned vectors, attaining stronger 34:task with an entirely new set of parameter values, which can become impractical when fine-tuning a 43:∗Equal contribution. 66:learned vectorslk,l v, andlff which respectively rescale (via element-wise multiplication, visualized as 67:⊙) the keys and values in attention mechanisms and the inner activations in position-wise feed-forward 92:that multiplies intermediate activations by learned vectors. (IA)3 attains stronger performance than 141:costs is to cache the key and value vectors for in-context examples. This is possible because decoder- 142:only Transformer language models have a causal masking pattern, so the model’s activations for the 144:tokens per in-context example would result in over 144 gigabytes of cached key and value vectors for 145:the GPT-3 model (32 examples× 512 tokens× 96 layers× 12288 dmodel× 32 bits each for the key 146:and value vectors). Separately, Min et al. [21] proposed ensemble ICL, where instead of using the 155:proposed adding adapters [22–24], which are small trainable feed-forward networks inserted between 160:tuning [29] concatenate learned continuous embeddings to the model’s input or activations to induce 287:graph. A more convenient alternative is provided by methods that directly modify the activations of 290:concatenating learned vectors to activation or embedding sequences and are therefore examples of 291:activation-modifying PEFT methods that allow for mixed-task batches. However, as we will discuss 296:As an alternative, we explored element-wise multiplication (i.e. rescaling) of the model’s activations 297:against a learned vector. Specifically, we consider adaptation of the forml⊙x wherel∈ Rd is a 298:learned task-specific vector,⊙ represents element-wise multiplication, andx∈ RT ×d is a length-T 299:sequence of activations. We use “broadcasting notation” [46] so that the (i,j )th entry ofl⊙x isljxi,j. 301:for each set of activations...

[tool] Search LoRA|low-rank|A|B|alpha|rank|Eq|equation|ΔW|Delta|zero|Gaussian|Kaiming|initial in lora_*.txt (completed) kind: search input: {"call_id":"call_bWnP0o9dE2sMNEN6N5a9w6Jp","process_id":"2585","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","rg -n "LoRA|low-rank|A|B|alpha|rank|Eq|equation|ΔW|Delta|zero|Gaussian|... output: 1:LORA: L OW-R ANK ADAPTATION OF LARGE LAN- 2:GUAGE MODELS 3:Edward Hu∗ Yelong Shen∗ Phillip Wallis Zeyuan Allen-Zhu 10:ABSTRACT 11:An important paradigm of natural language processing consists of large-scale pre- 12:training on general domain data and adaptation to particular tasks or domains. As 14:becomes less feasible. Using GPT-3 175B as an example – deploying indepen- 15:dent instances of fine-tuned models, each with 175B parameters, is prohibitively 16:expensive. We propose Low-Rank Adaptation, or LoRA, which freezes the pre- 17:trained model weights and injects trainable rank decomposition matrices into each 19:rameters for downstream tasks. Compared to GPT-3 175B fine-tuned with Adam, 20:LoRA can reduce the number of trainable parameters by 10,000 times and the 21:GPU memory requirement by 3 times. LoRA performs on-par or better than fine- 22:tuning in model quality on RoBERTa, DeBERTa, GPT-2, and GPT-3, despite hav- 25:rank-deficiency in language model adaptation, which sheds light on the efficacy of 26:LoRA. We release a package that facilitates the integration of LoRA with PyTorch 27:models and provide our implementations and model checkpoints for RoBERTa, 28:DeBERTa, and GPT-2 athttps://github.com/microsoft/LoRA. 46:tion. We only train A and B. 52:parameters as in the original model. As larger models are trained 54:GPT-2 (Radford et al., b) or RoBERTa large (Liu et al., 2019) to a 55:critical deployment challenge for GPT-3 (Brown et al., 2020) with 62:∗Equal contribution. 64:1While GPT-3 175B achieves non-trivial performance with few-shot learning, fine-tuning boosts its perfor- 65:mance significantly as shown in Appendix A. 72:We take inspiration from Li et al. (2018a); Aghajanyan et al. (2020) which show that the learned 74:change in weights during model adaptation also has a low “intrinsic rank”, leading to our proposed 75:Low-Rank Adaptation (LoRA) approach. LoRA allows us to train some dense layers in a neural ... (519 more lines)

[tool] Search DoRA|magnitude|direction|decompose|norm|V =|Eq|equation|initialize|column|row in dora_*.txt (completed) kind: search input: {"call_id":"call_u0hqS6Uap4DQRdjRTfjZS35I","process_id":"15602","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","rg -n "DoRA|magnitude|direction|decompose|norm|V =|Eq|equation|initial... output: 1:DoRA: Weight-Decomposed Low-Rank Adaptation 16:Rank Adaptation (DoRA). DoRA decomposes 18:nitude and direction, for fine-tuning, specifically 19:employing LoRA for directional updates to ef- 21:rameters. By employing DoRA, we enhance 24:ference overhead. DoRA consistently outper- 30:NVlabs/DoRA. 63:Figure 1. An overview of our proposed DoRA, which decomposes 64:the pre-trained weight into magnitude and direction components 66:direction component. Note that || · || c denotes the vector-wise 67:norm of a matrix across each column vector. 86:tially reparameterizes model weights into magnitude and di- 90:DoRA: Weight-Decomposed Low-Rank Adaptation 91:in magnitude and direction introduced by LoRA and FT. 96:Low-Rank Adaptation (DoRA), which begins by decompos- 97:ing the pre-trained weight into its magnitude and directional 99:size of the directional component in terms of parameters, 100:we exploit LoRA for the directional adaptation to enable 104:closely resembling FT, we have validated DoRA across a 107:experimental results show that DoRA consistently outper- 114:• We introduce DoRA, a novel PEFT method that incor- 121:• DoRA consistently surpasses LoRA on various tasks, 183:trix A is initialized with uniform Kaiming distribution (He 188:ditionally, based on Eq. (1), we can merge the learned ∆W 191:DoRA: Weight-Decomposed Low-Rank Adaptation 208:into magnitude and direction for accelerating optimization, 211:arate components, magnitude and direction, to reveal the 214:both magnitude and direction of the LoRA and FT weights ... (270 more lines)

[tool] List /media/wassname/SGIronWolf/projects5/2026/lora-lite/papers (running) input: {"call_id":"call_WDgDsyoegpxmYzNxHapO8Fv5","process_id":"37661","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","ls docs/papers"],"cwd":"/media/wassname/SGIronWolf/projects5/2026/lora-... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/papers

[tool] Search DeLoRA|lambda|Xi|Frobenius|normalize|norm|Eq|equation|initial|BXiA|rank-1|bounded|Kaiming in delora_*.txt (running) input: {"call_id":"call_kCjqhNBUefgB2d9cLgpLVQXu","process_id":"93391","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","rg -n "DeLoRA|lambda|Xi|Frobenius|normalize|norm|Eq|equation|initial|B...

[tool] Run tr '\000' ' ' < docs/papers/pissa_2404.02948.txt | rg -n "PiSSA|SVD|singular|principal|residual|W_res|Equation|Eq|initialize|A =|B =|W^res|Σ|U|V" (running) input: {"call_id":"call_IYEogQ1vzPNOesA5pz8BR3Rm","process_id":"70162","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","tr '\000' ' ' < docs/papers/pissa_2404.02948.txt | rg -n "PiSSA|SVD|s...

[tool] Search Householder|HRA|reflection|orthogonal|orthogonality|regular|Eq|equation|W'|R =|H_i|identity|initialize in hra_*.txt (running) input: {"call_id":"call_LyXBP8FEJOi8PqBIwdFguyLO","process_id":"39215","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","rg -n "Householder|HRA|reflection|orthogonal|orthogonality|regular|Eq|...

[tool] List /media/wassname/SGIronWolf/projects5/2026/lora-lite/papers (completed) kind: search input: {"call_id":"call_WDgDsyoegpxmYzNxHapO8Fv5","process_id":"37661","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","ls docs/papers"],"cwd":"/media/wassname/SGIronWolf/projects5/2026/lora-... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/papers output: delora_2503.18225.pdf delora_2503.18225.txt dora_2402.09353.pdf dora_2402.09353.txt hra_2405.17484.pdf hra_2405.17484.txt ia3_2205.05638.pdf ia3_2205.05638.txt lora_2106.09685.pdf lora_2106.09685.txt pissa_2404.02948.pdf pissa_2404.02948.txt

[tool] Search DeLoRA|lambda|Xi|Frobenius|normalize|norm|Eq|equation|initial|BXiA|rank-1|bounded|Kaiming in delora_*.txt (completed) kind: search input: {"call_id":"call_kCjqhNBUefgB2d9cLgpLVQXu","process_id":"93391","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","rg -n "DeLoRA|lambda|Xi|Frobenius|normalize|norm|Eq|equation|initial|B... output: 15:bounded approaches, such as ETHER, provide greater robustness but are limited 18:rank Adaptation (DeLoRA), a novel finetuning method that normalizes and scales 20:DeLoRA effectively decouples the angular learning from the adaptation strength, 23:tion tuning, we show that DeLoRA matches or surpasses performance of com- 25:https://github.com/ExplainableML/DeLoRA. 29:et al., 2023a;b; Radford et al., 2021; Rombach et al., 2022). However, the enormous size of these 41:Therefore, we propose DeLoRA, an enhanced version of LoRA that introduces a boundary on the 42:weight updates through normalization, decoupling the angular learning from the adaptation strength. 44:and merging at inference time. We motivate DeLoRA from two distinct perspectives: as an extension 45:of LoRA through the introduction of additional normalization, and as an evolution of ETHER by 47:improvements over both LoRA and ETHER. Additionally, we validate the advantages of DeLoRA 50:arXiv:2503.18225v2 [cs.LG] 19 May 2025 55:LoRA DeLoRA 67:norm 72:method DeLoRA. In addition to the low-rank matrices B, A, we introduce a normalization Ξ and a 75:mulations of LoRA and ETHER and derive a novel PEFT method, DeLoRA; (ii) we demonstrate 76:DeLoRA enhanced robustness and decoupling compared to alternatives; (iii) we extensively ablate 77:the formulation of DeLoRA by deriving it from both LoRA and ETHER; (iv) we evaluate DeLoRA 85:describe how we derive our proposed DeLoRA method from both perspectives (Section 2.2), along 105:avoiding catastrophic overwriting of the pretrained weights. In our proposed DeLoRA, we mitigate 109:ments, Bini et al. (2024) propose to employ bounded transformations for finetuning, namely ETHER 112:and ETHER+. ETHER (left side in Eq. (2)) and ETHER+ (right side) introduce multiplicative trans- 120:vectors) are bounded in terms of their distance to the identity transformation, as per 125:where the subscript F denotes the Frobenius norm. This upper bound on the transformation distanc...

[tool] Run tr '\000' ' ' < docs/papers/pissa_2404.02948.txt | rg -n "PiSSA|SVD|singular|principal|residual|W_res|Equation|Eq|initialize|A =|B =|W^res|Σ|U|V" (completed) kind: execute input: {"call_id":"call_IYEogQ1vzPNOesA5pz8BR3Rm","process_id":"70162","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","tr '\000' ' ' < docs/papers/pissa_2404.02948.txt | rg -n "PiSSA|SVD|s... output: 1:PiSSA: Principal Singular Values and Singular 2:Vectors Adaptation of Large Language Models 4:1Institute for Artificial Intelligence, Peking University 5:2State Key Laboratory of General Artificial Intelligence, Peking University 6:https://github.com/GraphPKU/PiSSA 11:r ≪ min(m, n), A is initialized with Gaussian noise, and B with zeros. LoRA 14:Singular values and Singular vectors Adaptation (PiSSA). PiSSA shares the same 15:architecture as LoRA, but initializes the adaptor matrices A and B with the princi- 17:residual matrix W res ∈ Rm×n which is frozen during fine-tuning. Compared to 18:LoRA, PiSSA updates the principal components while freezing the “residual” 20:periments of PiSSA and LoRA across 11 different models, ranging from 184M to 21:70B, encompassing 5 NLG and 8 NLU tasks, reveal that PiSSA consistently out- 23:Gemma-7B fine-tuned with PiSSA achieves an accuracy of 77.7%, surpassing 24:LoRA’s 74.53% by 3.25%. Due to the same architecture, PiSSA is also compat- 26:Compared to QLoRA, QPiSSA (PiSSA with 4-bit quantization) exhibits smaller 28:QPiSSA attains an accuracy of 86.05%, exceeding the performance of QLoRA at 29:81.73%. Leveraging a fast SVD technique, PiSSA can be initialized in only a few 30:seconds, presenting a negligible cost for transitioning from LoRA to PiSSA. 36:of a LLaMA 65B parameter model requires over 780 GB of GPU memory [ 10], and the VRAM 62:𝑆[:𝑟]𝑟 (c) PiSSA 63:Figure 1: The comparison among Full Fine-tuning, training with LoRA, and PiSSA. In this visualiza- 66:LoRA to 4-bit, whereas QPiSSA quantizes the residual matrix in PiSSA. 67:Table 1: Comparison of similarities and differences between PiSSA and LoRA. In this table,bold 68:highlights the model’s primary component, while underlinedenotes the residual component. 69:LoRA PiSSA 71:A ∼ N (0, σ2) ∈ Rm×r A = U[:,:r] S1/2 74:B = 0 ∈ Rr×n B = S1/2 75:[:r,:r] V ⊤ ... (426 more lines)

[tool] Search Householder|HRA|reflection|orthogonal|orthogonality|regular|Eq|equation|W'|R =|H_i|identity|initialize in hra_*.txt (completed) kind: search input: {"call_id":"call_LyXBP8FEJOi8PqBIwdFguyLO","process_id":"39215","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","rg -n "Householder|HRA|reflection|orthogonal|orthogonality|regular|Eq|... output: binary file matches (found "\0" byte around offset 8064)

[tool] Run tr '\000' ' ' < docs/papers/hra_2405.17484.txt | rg -n "Householder|HRA|reflection|orthogonal|orthogonality|regular|Equation|Eq|W|R =|H_i|identity|initialize|product" (running) input: {"call_id":"call_OMzCypXuxmB4HY1su5fUTB41","process_id":"87863","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","tr '\000' ' ' < docs/papers/hra_2405.17484.txt | rg -n "Householder|H...

[tool] Run tr '\000' ' ' < docs/papers/hra_2405.17484.txt | rg -n "Householder|HRA|reflection|orthogonal|orthogonality|regular|Equation|Eq|W|R =|H_i|identity|initialize|product" (completed) kind: execute input: {"call_id":"call_OMzCypXuxmB4HY1su5fUTB41","process_id":"87863","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","tr '\000' ' ' < docs/papers/hra_2405.17484.txt | rg -n "Householder|H... output: 2:Adaptation via Householder Reflection Adaptation 8:While following different technical routes, both low-rank and orthogonal adaptation 12:method based on Householder reflections. Given a pre-trained model, our method 13:fine-tunes its layers by multiplying each frozen weight matrix with an orthogonal 14:matrix constructed by a chain of learnable Householder reflections (HRs). This 15:HR-based orthogonal fine-tuning is equivalent to an adaptive low-rank adaptation. 16:Moreover, we show that the orthogonality of the reflection planes corresponding 17:to the HRs impacts the model capacity and regularity. The analysis motivates us 18:to regularize the orthogonality of the HRs, leading to different implementations 19:of the proposed Householder reflection adaptation (HRA) method. Compared 20:with state-of-the-art methods, HRA achieves superior performance with fewer 23:DaShenZi721/HRA, and the method has been merged into the PEFT package. 38:in the inference phase. Currently, given a parameter matrix of a pre-trained model, i.e., W ∈ Rdout×d, 45:AAAB83icbVDLSsNAFL2pr1pfVZduBovgqiQircuiG5cV7AOaUCbTSTt0MgnzEErob7hxoYhbf8adf+OkzUJbDwwczrmXe+aEKWdKu+63U9rY3NreKe9W9vYPDo+qxyddlRhJaIckPJH9ECvKmaAdzTSn/VRSHIec9sLpXe73nqhULBGPepbSIMZjwSJGsLaS78dYT8IoM/OhHFZrbt1dAK0TryA1KNAeVr/8UUJMTIUmHCs18NxUBxmWmhFO5xXfKJpiMsVjOrBU4JiqIFtknqMLq4xQlEj7hEYL9fdGhmOlZnFoJ/OMatXLxf+8gdHRTZAxkRpNBVkeigxHOkF5AWjEJCWazyzBRDKbFZEJlphoW1PFluCtfnmddK/qXqPeeLiutW6LOspwBudwCR40oQX30IYOEEjhGV7hzTHOi/PufCxHS06xcwp/4Hz+AIvhkgk= 47:AAAB83icbVDLSsNAFL2pr1pfVZduBovgqiRFqsuiG5cV7AOaUCbTSTt0MgnzEErob7hxoYhbf8adf+OkzUJbDwwczrmXe+aEKWdKu+63U9rY3NreKe9W9vYPDo+qxyddlRhJaIckPJH9ECvKmaAdzTSn/VRSHIec9sLpXe73nqhULBGPepbSIMZjwSJGsLaS78dYT8IoM/NhY1ituXV3AbROvILUoEB7WP3yRwkxMRWacKzUwHNTHWRYakY4nVd8o2iKyRSP6cBSgWOqgmyReY4urDJCUSLtExot1N8bGY6VmsWhncwzqlUvF//zBkZHN0HGRGo0FWR5KDIc6QTlBaARk5RoPrMEE8lsVkQmWGKibU0V...

[tool] Read dora_2402.09353.txt (running) input: {"call_id":"call_eZ8F71QoWNQkvORpG7wnzPKP","process_id":"73985","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","sed -n '220,250p' docs/papers/dora_2402.09353.txt"],"cwd":"/media/wassn... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/docs/papers/dora_2402.09353.txt

[tool] Read delora_2503.18225.txt (running) input: {"call_id":"call_dRseeZXlFuJtlcV6O6B7Pp6e","process_id":"96401","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","sed -n '282,300p' docs/papers/delora_2503.18225.txt"],"cwd":"/media/was... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/docs/papers/delora_2503.18225.txt

[tool] Read ia3_2205.05638.txt (running) input: {"call_id":"call_bQPmoF4wuY4LJjDU4wKFTGb0","process_id":"31176","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","sed -n '296,312p' docs/papers/ia3_2205.05638.txt"],"cwd":"/media/wassna... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/docs/papers/ia3_2205.05638.txt

[tool] Read lora_2106.09685.txt (running) input: {"call_id":"call_UdRYpT88AHSMm73Ft3sb0vdK","process_id":"42170","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","sed -n '190,210p' docs/papers/lora_2106.09685.txt"],"cwd":"/media/wassn... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/docs/papers/lora_2106.09685.txt

[tool] Read dora_2402.09353.txt (completed) kind: read input: {"call_id":"call_eZ8F71QoWNQkvORpG7wnzPKP","process_id":"73985","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","sed -n '220,250p' docs/papers/dora_2402.09353.txt"],"cwd":"/media/wassn... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/docs/papers/dora_2402.09353.txt output: sed: /tmp/.mount_vscodiOHg5sd/lib/x86_64-linux-gnu/libselinux.so.1: no version information available (required by sed) = ||W ||c W ||W ||c (2) where m ∈ R1×k is the magnitude vector, V ∈ Rd×k is the directional matrix, with || · ||c being the vector-wise norm of a matrix across each column. This decomposition ensures that each column of V /||V ||c remains a unit vector, and the corresponding scalar in m defines the magnitude of each vector. For our weight decomposition analysis, we select the VL- BART model fine-tuned on four image-text tasks as outlined in (Sung et al., 2022) for a case study. Following (Sung et al., 2022), which applies LoRA only to the query/value weight matrix in the self-attention module. We decompose the pre- trained weight W0, the full fine-tuned weight WFT, and the merged LoRA weight WLoRA of query/value weight matrix using Eq. (2). The magnitude and directional variations between W0 and WFT can be defined as follows: ∆M t FT = Pk n=1 |mn,t FT − mn 0 | k (3) ∆Dt ... (4 more lines)

[tool] Read delora_2503.18225.txt (completed) kind: read input: {"call_id":"call_dRseeZXlFuJtlcV6O6B7Pp6e","process_id":"96401","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","sed -n '282,300p' docs/papers/delora_2503.18225.txt"],"cwd":"/media/was... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/docs/papers/delora_2503.18225.txt output: sed: /tmp/.mount_vscodiOHg5sd/lib/x86_64-linux-gnu/libselinux.so.1: no version information available (required by sed) DeLoRA formulation. Summarizing, our proposed DeLoRA finetuning method consists in learn- ing a normalized low-rank matrix BΞA and a scale λ, updating the pretrained weights as in W + λ∥ ¯W ∥ r BΞA ⊺ x + b (15) This formulation inherently constrains the learnable finetuning updates in aλ∥ ¯W ∥-sized ball, where ¯W is the norm of the pretrained weights, achieving a decoupling of the transformation strength from the angular learning. In more detail, the key components are: • Normalization: Ξ is a r-dimensional diagonal matrix that normalizes LoRA’s inner low- dimensional bottleneck (Eq. (5)), bounding the Frobenius norm of BΞA to r (Eq. (6)). • Scaling Factors: (i) 1/r is used to remove the rank dependency on the boundary dimensionality, (ii) ∥ ¯W ∥ to make the weight updates proportional to the pretrained weights, and (iii)λ to control the adaptation strength and allow for a layer-specific boundary adaptation (Eq. (7)) • Initialization: Pretrained initialization follows by merging to the pretrained weights a frozen copy of the initialized finetuning adaptation matrices (Eq. (9)). DoRA vs DeLoRA discussion. DoRA (Liu et al., 2024a), similarly to our work, addresses fine- tuning targeting the decoupling of angular and magnitude components, by using a formulation that

[tool] Read ia3_2205.05638.txt (completed) kind: read input: {"call_id":"call_bQPmoF4wuY4LJjDU4wKFTGb0","process_id":"31176","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","sed -n '296,312p' docs/papers/ia3_2205.05638.txt"],"cwd":"/media/wassna... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/docs/papers/ia3_2205.05638.txt output: sed: /tmp/.mount_vscodiOHg5sd/lib/x86_64-linux-gnu/libselinux.so.1: no version information available (required by sed) As an alternative, we explored element-wise multiplication (i.e. rescaling) of the model’s activations against a learned vector. Specifically, we consider adaptation of the forml⊙x wherel∈ Rd is a learned task-specific vector,⊙ represents element-wise multiplication, andx∈ RT ×d is a length-T sequence of activations. We use “broadcasting notation” [46] so that the (i,j )th entry ofl⊙x isljxi,j. In preliminary experiments, we found it was not necessary to introduce a learned rescaling vector for each set of activations in the Transformer model. Instead, we found it was sufficient to introduce rescaling vectors on the keys and values in self-attention and encoder-decoder attention mechanisms and on the intermediate activation of the position-wise feed-forward networks. Specifically, using the notation from Vaswani et al. [33], we introduce three learned vectors lk∈ Rdk,l v∈ Rdv, and lff∈ Rdff , which are introduced into the attention mechanisms as: softmax (Q(lk⊙K T )√dk ) (lv⊙V ) and in the position-wise feed-forward networks as (lff⊙γ(W1x))W2, whereγ is the feed-forward network nonlinearity. We introduce a separate set oflk,l v, andlff vectors in each Transformer layer block. This adds a total ofL(dk +dv +dff ) new parameters for aL-layer-block Transformer encoder

[tool] Read lora_2106.09685.txt (completed) kind: read input: {"call_id":"call_UdRYpT88AHSMm73Ft3sb0vdK","process_id":"42170","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","sed -n '190,210p' docs/papers/lora_2106.09685.txt"],"cwd":"/media/wassn... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/docs/papers/lora_2106.09685.txt output: sed: /tmp/.mount_vscodiOHg5sd/lib/x86_64-linux-gnu/libselinux.so.1: no version information available (required by sed) We describe the simple design of LoRA and its practical benefits. The principles outlined here apply to any dense layers in deep learning models, though we only focus on certain weights in Transformer language models in our experiments as the motivating use case. 4.1 L OW-R ANK -PARAMETRIZED UPDATE MATRICES A neural network contains many dense layers which perform matrix multiplication. The weight matrices in these layers typically have full-rank. When adapting to a specific task, Aghajanyan et al. (2020) shows that the pre-trained language models have a low “instrisic dimension” and can still learn efficiently despite a random projection to a smaller subspace. Inspired by this, we hypothe- size the updates to the weights also have a low “intrinsic rank” during adaptation. For a pre-trained weight matrix W0∈ Rd×k, we constrain its update by representing the latter with a low-rank de- composition W0 + ∆W = W0 + BA, where B∈ Rd×r, A∈ Rr×k, and the rank r≪ min(d, k). During training, W0 is frozen and does not receive gradient updates, whileA and B contain trainable parameters. Note both W0 and ∆W = BA are multiplied with the same input, and their respective output vectors are summed coordinate-wise. For h = W0x, our modified forward pass yields: h = W0x + ∆W x = W0x + BAx (3) We illustrate our reparametrization in Figure 1. We use a random Gaussian initialization for A and zero for B, so ∆W = BA is zero at the beginning of training. We then scale ∆W x by α r , where α is a constant in r. When optimizing with Adam, tuning α is roughly the same as tuning the learning rate if we scale the initialization appropriately. As a result, we simply set α to the first r we try and do not tune it. This scaling helps to reduce the need to retune hyperparameters when we vary

[tool] Run tr '\000' ' ' < docs/papers/pissa_2404.02948.txt | sed -n '224,250p' (running) input: {"call_id":"call_XuGUouRx8rVTGidWifmXxTHK","process_id":"10872","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","tr '\000' ' ' < docs/papers/pissa_2404.02948.txt | sed -n '224,250p'"]...

[tool] Run tr '\000' ' ' < docs/papers/hra_2405.17484.txt | sed -n '239,266p' (running) input: {"call_id":"call_YUdE51vQ2pQzxJJ0de05qxBT","process_id":"84041","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","tr '\000' ' ' < docs/papers/hra_2405.17484.txt | sed -n '239,266p'"],"...

[tool] Read dora_2402.09353.txt (running) input: {"call_id":"call_PHQxP0pE81Ax1UO7FOrwQoyg","process_id":"65692","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","sed -n '370,391p' docs/papers/dora_2402.09353.txt"],"cwd":"/media/wassn... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/docs/papers/dora_2402.09353.txt

[tool] Run tr '\000' ' ' < docs/papers/hra_2405.17484.txt | sed -n '417,445p' (running) input: {"call_id":"call_RoD8Og7c3808QGTVmwmNrSUR","process_id":"43418","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","tr '\000' ' ' < docs/papers/hra_2405.17484.txt | sed -n '417,445p'"],"...

[tool] Run tr '\000' ' ' < docs/papers/hra_2405.17484.txt | sed -n '239,266p' (completed) kind: execute input: {"call_id":"call_YUdE51vQ2pQzxJJ0de05qxBT","process_id":"84041","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","tr '\000' ' ' < docs/papers/hra_2405.17484.txt | sed -n '239,266p'"],"... output: sed: /tmp/.mount_vscodiOHg5sd/lib/x86_64-linux-gnu/libselinux.so.1: no version information available (required by sed) a specular reflection hyperplane, denoted as H. For any x ∈ Rd, Hx corresponds to reflecting x across the hyperplane H, which reverses the component of x that is orthogonal to the hyperplane. Because H is an orthogonal matrix, it is natural for us to implement orthogonal adaptation based on it — we can treat H as an adapter and multiply it with the weight matrix of the pre-trained model. Moreover, since the set of all d × d orthogonal matrices, denoted as Od×d, satisfies all the axioms of a group which is a compact Lie group of dimension d(d − 1)/2, the product of orthogonal matrices is also an orthogonal matrix [1]. Therefore, we can enhance the capacity of the adapter by constructing a chain of r trainable Householder reflections, leading to our HRA method. As shown in Figure 1a, given a weight matrix W ∈ Rdout×d and an input x ∈ Rd, the forward step of HRA is z = W H(r)x = W Yr i=1 Hi  x = W Yr i=1 (I − 2uiu⊤ i )  x, with {ui ∈ Sd−1}r i=1. (1) Although (1) involves the chained product of r + 1 dense matrices, we can leverage the struc- ture of Householder reflection to simplify the computation. Let x(0) = x and x(j+1) = (I − 2ur−ju⊤ r−j)x(j) for j = 0, ..., r − 1. We implement (1) by the following two steps: 1) x(j+1) = x(j) − 2⟨ur−j, x(j)⟩ur−j, for j = 0, ..., r − 1. 2) z = W x(r). (2) ... (1 more lines)

[tool] Run tr '\000' ' ' < docs/papers/pissa_2404.02948.txt | sed -n '224,250p' (completed) kind: execute input: {"call_id":"call_XuGUouRx8rVTGidWifmXxTHK","process_id":"10872","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","tr '\000' ' ' < docs/papers/pissa_2404.02948.txt | sed -n '224,250p'"]... output: sed: /tmp/.mount_vscodiOHg5sd/lib/x86_64-linux-gnu/libselinux.so.1: no version information available (required by sed) 3 PiSSA: Principal Singular Values and Singular Vectors Adaptation This section formally presents our Principal Singular values and Singular vectors Adaptation method. PiSSA computes the singular value decomposition (SVD) of matrices W within the self-attention and multilayer perceptron (MLP) layers. The (economy size) SVD of a matrix W ∈ Rm×n is given by W = U SV ⊤, where U ∈ Rm×min(m,n), V ∈ Rn×min(m,n) are the singular vectors with orthonormal columns, and V ⊤ is the transpose of V . S = diag(s) ∈ Rmin(m,n)×min(m,n), where the operation diag(s) transforms s to a diagonal matrix S, and s ∈ Rmin(m,n) ≥0 represents the singular values arranged in descending order. When the top r singular values s[:r] are significantly larger than the remaining singular values s[r:], we denote the intrinsic rank of W as r. Consequently, S, along with U and V , can be divided into two groups: the principal singular values and vectors— {U[:,:r], S[:r,:r], V[:,:r]}, and the residual singular values and vectors— {U[:,r:], S[r:,r:], V[:,r:]}, where the matrix slicing notations are the same as those in PyTorch and [: r] denotes the first r dimensions. The principal singular values and vectors are utilized to initialize the injected adapter consisting of A ∈ Rm×r and B ∈ Rr×n: A = U[:,:r] S1/2 [:r,:r] ∈ Rm×r, (2) B = S1/2 [:r,:r] V ⊤ [:,:r] ∈ Rr×n. (3) The residual singular values and vectors are used to build the residual matrix which is frozen during fine-tuning: W res = U[:,r:] S[r:,r:] V ⊤ [:,r:] ∈ Rm×n. (4) As indicated by Equation 5, the integration of AB with the residual matrix also preserves the full capability of the pre-trained model in the beginning of fine-tuning: Y = XW = X(W res + W pri) = X(W res + AB). (5)

[tool] Read dora_2402.09353.txt (completed) kind: read input: {"call_id":"call_PHQxP0pE81Ax1UO7FOrwQoyg","process_id":"65692","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","sed -n '370,391p' docs/papers/dora_2402.09353.txt"],"cwd":"/media/wassn... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/docs/papers/dora_2402.09353.txt output: sed: /tmp/.mount_vscodiOHg5sd/lib/x86_64-linux-gnu/libselinux.so.1: no version information available (required by sed) & Kingma, 2016) lies in their training approaches. Weight normalization trains both components from scratch, mak- ing the method sensitive to different initializations. Con- versely, DoRA avoids such initialization concerns since both components begin with pre-trained weights. We initialize DoRA with pre-trained weight W0 as outlined in Eq. (2), where m = ||W0||c and V = W0 after initialization. We then keep V frozen and m a trainable vector. The directional component is then updated through LoRA. DoRA can be formulated similar to Eq. (1) as: W ′ = m V + ∆V ||V + ∆V ||c = m W0 + BA ||W0 + BA||c (5) where ∆V is the incremental directional update learned by multiplying two low-rank matrices B and A, and the underlined parameters denote the trainable parameters. The matrices B ∈ Rd×r and A ∈ Rr×k are initialized in line with LoRA’s strategy to ensure thatW ′ equals W0 before the finetuning. Furthermore, DoRA can be merged with the pre-trained weight before inference, thereby not introducing

[tool] Run tr '\000' ' ' < docs/papers/hra_2405.17484.txt | sed -n '417,445p' (completed) kind: execute input: {"call_id":"call_RoD8Og7c3808QGTVmwmNrSUR","process_id":"43418","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","tr '\000' ' ' < docs/papers/hra_2405.17484.txt | sed -n '417,445p'"],"... output: sed: /tmp/.mount_vscodiOHg5sd/lib/x86_64-linux-gnu/libselinux.so.1: no version information available (required by sed) Motivated by the above analysis, we can implement HRA with an orthogonality regularizer. Typically, given a pre-trained model M, we can adapt L weight matrices of the model based on a dataset D by solving the following optimization problem: min{U (l) r }L l=1 Loss(D; {U (l) r }L l=1) + λ XL l=1 ∥Ir − (U (l) r )⊤U (l) r ∥2 F , (6) where U (l) r denotes the parameters of HRA for the l-th weight matrix. In (6), the first term denotes the loss function, while the second term is the proposed regularizer that encourages the orthogonality of all U (l) r ’s, whose significance is controlled byλ > 0. Because it does not change the forward step of HRA, this regularizer only increases the adaptation cost slightly. As shown in Figure 1a, by controlling the strength of the orthogonality regularizer, we can achieve a trade-off between the model capacity and regularity. When λ = 0, the feasible domain of Ur is the set of column-normalized matrices, and accordingly, the model capacity is maximized. In contrast, when λ → ∞, the feasible domain of Ur is the set of orthogonal matrices (i.e., Od×r), leading to the strongest regularity. When λ = ∞, we implement a strictly-orthogonal HRA based on Gram- Schmidt (GS) orthogonalization. For each layer’s HRA adapter, we initialize its parameter matrix as ... (2 more lines)

[tool] Search === variant=|t=0 identity|save/load|loss[0]|Linear8bitLt|Linear4bit|ALL PASS|variant \t in smoke.log (running) input: {"call_id":"call_Cq3AKAdomLL3nfVH6sdVw5Og","process_id":"52954","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","rg -n "=== variant=|t=0 identity|save/load|loss\[0\]|Linear8bitLt|Li...

[tool] Search ^(variant|lora|pissa|delora|ia3|dora|hra)|ALL QWEN in qwen_probe.log (running) input: {"call_id":"call_UybdTwAPyZghPblXqP44hq58","process_id":"59149","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","rg -n "^(variant|lora|pissa|delora|ia3|dora|hra)|ALL QWEN" logs/qwen_...

[tool] Read smoke.log (running) input: {"call_id":"call_7n1MahUfgq21v3LwRKTww9W4","process_id":"42160","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","nl -ba logs/smoke.log | sed -n '1,120p'"],"cwd":"/media/wassname/SGIron... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/logs/smoke.log

[tool] Read qwen_probe.log (running) input: {"call_id":"call_w3TWFELhGDScRzTyE8wD25oI","process_id":"41693","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","nl -ba logs/qwen_probe.log | sed -n '1,80p'"],"cwd":"/media/wassname/SG... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/logs/qwen_probe.log

[tool] Search === variant=|t=0 identity|save/load|loss[0]|Linear8bitLt|Linear4bit|ALL PASS|variant \t in smoke.log (completed) kind: search input: {"call_id":"call_Cq3AKAdomLL3nfVH6sdVw5Og","process_id":"52954","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","rg -n "=== variant=|t=0 identity|save/load|loss\[0\]|Linear8bitLt|Li... output: 6:=== variant=lora dtype=torch.float32 === 8: t=0 identity: max|y_adapt - y_base| = 0.000e+00 (base scale 4.609e+00) 10: save/load: max|y_loaded - y_adapt| = 0.000e+00 12: loss[0]=1.0882 loss[-1]=1.0220 drop=6.1% 15:=== variant=pissa dtype=torch.float32 === 17: t=0 identity: max|y_adapt - y_base| = 1.550e-06 (base scale 4.609e+00) 19: save/load: max|y_loaded - y_adapt| = 0.000e+00 21: loss[0]=1.0823 loss[-1]=0.9583 drop=11.5% 24:=== variant=delora dtype=torch.float32 === 26: t=0 identity: max|y_adapt - y_base| = 0.000e+00 (base scale 4.609e+00) 28: save/load: max|y_loaded - y_adapt| = 0.000e+00 30: loss[0]=1.0909 loss[-1]=0.0277 drop=97.5% 33:=== variant=ia3 dtype=torch.float32 === 35: t=0 identity: max|y_adapt - y_base| = 0.000e+00 (base scale 4.609e+00) 37: save/load: max|y_loaded - y_adapt| = 0.000e+00 39: loss[0]=1.0823 loss[-1]=0.1228 drop=88.7% 42:=== variant=dora dtype=torch.float32 === 44: t=0 identity: max|y_adapt - y_base| = 0.000e+00 (base scale 4.609e+00) 46: save/load: max|y_loaded - y_adapt| = 0.000e+00 48: loss[0]=1.0882 loss[-1]=0.3996 drop=63.3% 51:=== variant=hra dtype=torch.float32 === 53: t=0 identity: max|y_adapt - y_base| = 0.000e+00 (base scale 4.609e+00) 55: save/load: max|y_loaded - y_adapt| = 0.000e+00 57: loss[0]=1.0882 loss[-1]=0.0305 drop=97.2% 68: Linear8bitLt lora : identity_err=0.000e+00 grad_nonzero=True 69: Linear8bitLt delora: identity_err=0.000e+00 grad_nonzero=True 70: Linear8bitLt ia3 : identity_err=0.000e+00 grad_nonzero=True 71: Linear8bitLt hra : identity_err=0.000e+00 grad_nonzero=True ... (9 more lines)

[tool] Search ^(variant|lora|pissa|delora|ia3|dora|hra)|ALL QWEN in qwen_probe.log (completed) kind: search input: {"call_id":"call_UybdTwAPyZghPblXqP44hq58","process_id":"59149","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","rg -n "^(variant|lora|pissa|delora|ia3|dora|hra)|ALL QWEN" logs/qwen_... output: 15:variant targets trainable id_err perturb loss0 lossN drop% grad dθ reload out 16:lora 2 20480 0 0.2969 5.25 2.509 52.22 1.349 5.205 0 outputs/qwen_train_probe/lora_adapter.pt 17:pissa 2 20480 0.3125 0.75 5.25 2.958 43.66 6.124 5.909 0 outputs/qwen_train_probe/pissa_adapter.pt 18:delora 2 20484 0.7188 0.4688 5.236 3.364 35.75 2.143 9.086 0 outputs/qwen_train_probe/delora_adapter.pt 19:ia3 2 3072 0 0.375 5.25 4.473 14.79 0.463 5.926 0 outputs/qwen_train_probe/ia3_adapter.pt 20:dora 2 23552 0 0.4062 5.25 2.189 58.3 2.052 7.734 0 outputs/qwen_train_probe/dora_adapter.pt 21:hra 2 8194 0 0.3594 5.25 4.136 21.23 0.09808 4.49 0 outputs/qwen_train_probe/hra_adapter.pt 22:ALL QWEN PROBES PASS

[tool] Read smoke.log (completed) kind: read input: {"call_id":"call_7n1MahUfgq21v3LwRKTww9W4","process_id":"42160","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","nl -ba logs/smoke.log | sed -n '1,120p'"],"cwd":"/media/wassname/SGIron... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/logs/smoke.log output: sed: /tmp/.mount_vscodiOHg5sd/lib/x86_64-linux-gnu/libselinux.so.1: no version information available (required by sed) 1 /media/wassname/SGIronWolf/projects5/2026/lora-lite/.venv/lib/python3.13/site-packages/bitsandbytes/autograd/_functions.py:123: UserWarning: MatMul8bitLt: inputs will be cast from torch.float32 to float16 during quantization 2 warnings.warn(f"MatMul8bitLt: inputs will be cast from {A.dtype} to float16 during quantization") 3 /media/wassname/SGIronWolf/projects5/2026/lora-lite/.venv/lib/python3.13/site-packages/bitsandbytes/backends/cuda/ops.py:213: FutureWarning: _check_is_size will be removed in a future PyTorch release along with guard_size_oblivious. Use _check(i >= 0) instead. 4 torch._check_is_size(blocksize) 5 6 === variant=lora dtype=torch.float32 === 7 attached 28 targets, trainable params=17408 8 t=0 identity: max|y_adapt - y_base| = 0.000e+00 (base scale 4.609e+00) 9 SHOULD: err<4.6e-06. PASS. 10 save/load: max|y_loaded - y_adapt| = 0.000e+00 11 SHOULD: err2<4.6e-06. PASS. 12 loss[0]=1.0882 loss[-1]=1.0220 drop=6.1% 13 SHOULD: drop>5%. PASS. 14 15 === variant=pissa dtype=torch.float32 === 16 attached 28 targets, trainable params=17408 17 t=0 identity: max|y_adapt - y_base| = 1.550e-06 (base scale 4.609e+00) 18 SHOULD: err<2.3e-03. PASS. 19 save/load: max|y_loaded - y_adapt| = 0.000e+00 20 SHOULD: err2<2.3e-03. PASS. 21 loss[0]=1.0823 loss[-1]=0.9583 drop=11.5% 22 SHOULD: drop>5%. PASS. 23 24 === variant=delora dtype=torch.float32 === 25 attached 28 targets, trainable params=17436 26 t=0 identity: max|y_adapt - y_base| = 0.000e+00 (base scale 4.609e+00) 27 SHOULD: err<4.6e-06. PASS. ... (54 more lines)

[tool] Read qwen_probe.log (completed) kind: read input: {"call_id":"call_w3TWFELhGDScRzTyE8wD25oI","process_id":"41693","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","nl -ba logs/qwen_probe.log | sed -n '1,80p'"],"cwd":"/media/wassname/SG... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/logs/qwen_probe.log output: sed: /tmp/.mount_vscodiOHg5sd/lib/x86_64-linux-gnu/libselinux.so.1: no version information available (required by sed) 1 New task added (id 84). 2 SHOULD: exact q_proj/v_proj layer-0 targets, lora-only grads, lossN<loss0, perturb>0, reload<tol. ELSE hook/target/train/save bug. 3 Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 11183.76it/s] 4 Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 10483.91it/s] 5 Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 11231.62it/s] 6 Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 11419.02it/s] 7 Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 11501.48it/s] 8 Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 10138.41it/s] 9 Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 11177.81it/s] 10 Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 10532.84it/s] 11 Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 10290.29it/s] 12 Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 11146.68it/s] 13 Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 10274.97it/s] 14 Loading weights: 0%| | 0/311 [00:00<?, ?it/s] Loading weights: 100%|██████████| 311/311 [00:00<00:00, 10701.60it/s] 15 variant targets trainable id_err perturb loss0 lossN drop% grad... One important pattern has emerged: the toy smoke and the Qwen probe do not agree for PiSSA and DeLoRA identity behavior. I’m checking the probe script/config now because that difference affects whether the log is a pass or a paper-faithfulness warning.

[tool] Search qwen|qwen_train_probe|LoraLiteConfig|lambda0|alpha|variant in . (running) input: {"call_id":"call_icH4JA6mT0tbZ9MkdbCU47eS","process_id":"97197","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","rg -n "qwen|qwen_train_probe|LoraLiteConfig|lambda0|alpha|variant" -S...

[tool] Search qwen|qwen_train_probe|LoraLiteConfig|lambda0|alpha|variant in . (completed) kind: search input: {"call_id":"call_icH4JA6mT0tbZ9MkdbCU47eS","process_id":"97197","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","rg -n "qwen|qwen_train_probe|LoraLiteConfig|lambda0|alpha|variant" -S... output: ./README.md:19:cfg = ll.LoraLiteConfig(variant="lora", r=8, alpha=16, dtype=torch.bfloat16) ./README.md:35:just qwen-probe # Qwen/Qwen3-0.6B train/save-load probe ./README.md:57:Useful LoraLiteConfig fields: ./README.md:78:See docs/developer_guide.md for the variant API, data-calibrated init, and adapter roadmap. ./docs/spec/20260426_lora_lite_plan.md:7:The core bet is that adapter variants should own the relationship between (x, layer.weight, layer.lora_*) and the layer output, while the library only handles targeting, parameter attachment, hooks, and save/load. ./docs/spec/20260426_lora_lite_plan.md:26:- Data-calibrated variants use group_init(model, targets, cfg, calibration_data); dataloaders stay out of cfg so checkpoints are serializable. ./docs/spec/20260426_lora_lite_plan.md:32:| LoraLiteConfig | done | src/lora_lite/config.py | ./docs/spec/20260426_lora_lite_plan.md:33:| Variant registry + ParamSpec | done | src/lora_lite/variant.py | ./docs/spec/20260426_lora_lite_plan.md:36:| LoRA | done | src/lora_lite/variants/lora.py | ./docs/spec/20260426_lora_lite_plan.md:37:| PiSSA | done, fp-only | src/lora_lite/variants/pissa.py | ./docs/spec/20260426_lora_lite_plan.md:38:| DeLoRA | done | src/lora_lite/variants/delora.py | ./docs/spec/20260426_lora_lite_plan.md:39:| IA3 | done | src/lora_lite/variants/ia3.py | ./docs/spec/20260426_lora_lite_plan.md:40:| DoRA | done, fp-only | src/lora_lite/variants/dora.py | ./docs/spec/20260426_lora_lite_plan.md:41:| HRA | done | src/lora_lite/variants/hra.py (output-side Householder, hook-only -> bnb-compatible) | ./docs/spec/20260426_lora_lite_plan.md:73:- Pytest coverage for LoRA, PiSSA, and DeLoRA correctness invariants. ./docs/spec/20260426_lora_lite_plan.md:75:- A real Qwen/Qwen3-0.6B probe that trains each current variant on layer-0 q_proj and v_proj. ./docs/spec/20260426_lora_lite_plan.md:91:| R4: current variants train on tiny task | 28 TinyModel targets; ...

[tool] Read qwen_train_probe.py (running) input: {"call_id":"call_VBAAqoYfZcyMHtv4vJKvZDyq","process_id":"87533","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","nl -ba scripts/qwen_train_probe.py | sed -n '20,45p'"],"cwd":"/media/wa... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/scripts/qwen_train_probe.py

[tool] Read qwen_train_probe.py (completed) kind: read input: {"call_id":"call_VBAAqoYfZcyMHtv4vJKvZDyq","process_id":"87533","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","nl -ba scripts/qwen_train_probe.py | sed -n '20,45p'"],"cwd":"/media/wa... files: /media/wassname/SGIronWolf/projects5/2026/lora-lite/scripts/qwen_train_probe.py output: sed: /tmp/.mount_vscodiOHg5sd/lib/x86_64-linux-gnu/libselinux.so.1: no version information available (required by sed) 20 21 22 def cfg_for_variant(variant: str, dtype: torch.dtype, r: int, alpha: float) -> ll.LoraLiteConfig: 23 return ll.LoraLiteConfig( 24 variant=variant, 25 r=r, 26 alpha=r if variant == "pissa" else alpha, 27 dtype=dtype, 28 target_roles=(), 29 target_names=(r"model.layers.0.self_attn.(q_proj|v_proj)$",), 30 layers=(0,), 31 variant_kwargs={"lambda0": 0.1} if variant == "delora" else {}, 32 ) 33 34 35 def adapter_state(model: torch.nn.Module) -> dict[str, torch.Tensor]: 36 return {k: v.detach().clone() for k, v in model.state_dict().items() if "lora_" in k} 37 38 39 def assert_only_lora_trainable(model: torch.nn.Module) -> None: 40 trainable = [name for name, p in model.named_parameters() if p.requires_grad] 41 assert trainable 42 assert all("lora_" in name for name in trainable), trainable[:20] 43 44 45 def assert_no_base_grads(model: torch.nn.Module) -> None:

[tool] Search dtype in qwen_train_probe.py (running) input: {"call_id":"call_DKgY6gkmUZdWaTwYoZS4fkZq","process_id":"82966","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","rg -n "dtype" scripts/qwen_train_probe.py"],"cwd":"/media/wassname/SG...

[tool] Search dtype in qwen_train_probe.py (completed) kind: search input: {"call_id":"call_DKgY6gkmUZdWaTwYoZS4fkZq","process_id":"82966","turn_id":"019dc96e-e7cd-79f2-b04d-65a1c4d26637","command":["/usr/bin/zsh","-lc","rg -n "dtype" scripts/qwen_train_probe.py"],"cwd":"/media/wassname/SG... output: 22:def cfg_for_variant(variant: str, dtype: torch.dtype, r: int, alpha: float) -> ll.LoraLiteConfig: 27: dtype=dtype, 74:def load_model(model_id: str, dtype: torch.dtype, device: str): 75: model = AutoModelForCausalLM.from_pretrained(model_id, dtype=dtype).to(device) 80:def run_variant(args, variant: str, input_ids: torch.Tensor, labels: torch.Tensor, dtype: torch.dtype): 81: model = load_model(args.model, dtype, args.device) 83: cfg = cfg_for_variant(variant, dtype, args.r, args.alpha) 147: loaded_model = load_model(args.model, dtype, args.device) 183: parser.add_argument("--torch-dtype", default="bfloat16") 196: dtype = getattr(torch, args.torch_dtype) 202: rows = [run_variant(args, variant, input_ids, labels, dtype) for variant in args.variants]

Per-Variant Paper-Faithfulness Audit

lora

1. Paper claim summary
   LoRA (docs/papers/lora_2106.09685.txt §4.1, eq.3): freeze W0, train low-rank B,A, and compute h = W0x + BAx; initialize A random and B zero so the adapter is identity at training start, then scale by alpha/r.

2. What our code does — src/lora_lite/variants/lora.py:19, src/lora_lite/variants/lora.py:31

"lora_A": ParamSpec((cfg.r, d_in), init="kaiming", trainable=True),
"lora_B": ParamSpec((d_out, cfg.r), init="zeros",  trainable=True),
scale = cfg.alpha / cfg.r
h = einsum(x, layer.lora_A, "... i, r i -> ... r")
return y + scale * delta

3. Match? Y
   Faithful. Kaiming is not literally “Gaussian”, but it is the standard LoRA-style nonzero A, zero B identity initialization and the scaling matches.

4. Smoke evidence
   Toy row from logs/smoke.log:6-12:

=== variant=lora dtype=torch.float32 ===
  t=0 identity: max|y_adapt - y_base| = 0.000e+00  (base scale 4.609e+00)
  save/load: max|y_loaded - y_adapt| = 0.000e+00
  loss[0]=1.0882  loss[-1]=1.0220  drop=6.1%

bnb rows from logs/smoke.log:68,74:

Linear8bitLt   lora  : identity_err=0.000e+00 grad_nonzero=True
Linear4bit     lora  : identity_err=0.000e+00 grad_nonzero=True

Qwen row from logs/qwen_probe.log:16:

lora     	        2	      20480	  0     	   0.2969	  5.25 	  2.509	  52.22	1.349  	5.205	       0	outputs/qwen_train_probe/lora_adapter.pt

Consistent with paper: identity at t=0, nonzero perturb after training, loss drops, reload exact.

5. Bugs / concerns
   No paper-faithfulness bugs found. Missing test: no explicit check that A itself receives zero gradient on the first step when B=0, then receives gradient after B moves, but this is expected LoRA behavior.

6. Confidence
   High — simple formula, direct implementation, logs exercise identity, gradient, training, bnb, and reload.

---

pissa

1. Paper claim summary
   PiSSA (docs/papers/pissa_2404.02948.txt §3, eqs.2-5): SVD-decompose W = U S V^T, initialize the adapter from the top-r singular values/vectors, freeze the residual W_res, and preserve the pretrained function initially via Y = X(W_res + AB).

2. What our code does — src/lora_lite/variants/pissa.py:25, src/lora_lite/variants/pissa.py:31

U, S, Vh = torch.linalg.svd(W, full_matrices=False)
B = (Ur * sqrtS).to(cfg.dtype)
A = (sqrtS[:, None] * Vhr).to(cfg.dtype)
layer.lora_B.data.copy_(B)
layer.weight.data.copy_((W - scale * BA).to(layer.weight.dtype))

3. Match? Partial
   Matches the SVD/residual idea only when alpha == r so scale == 1. This deviation is documented in the code comment at src/lora_lite/variants/pissa.py:43, but not in the top docstring. The implementation rejects bnb layers instead of implementing QPiSSA; that is documented in code and is acceptable for a small v1, but not the quantized PiSSA extension.

4. Smoke evidence
   Toy row from logs/smoke.log:15-21:

=== variant=pissa dtype=torch.float32 ===
  t=0 identity: max|y_adapt - y_base| = 1.550e-06  (base scale 4.609e+00)
  save/load: max|y_loaded - y_adapt| = 0.000e+00
  loss[0]=1.0823  loss[-1]=0.9583  drop=11.5%

bnb rows from logs/smoke.log:72,78:

Linear8bitLt   pissa : fail-loud OK (TypeError)
Linear4bit     pissa : fail-loud OK (TypeError)

Qwen row from logs/qwen_probe.log:17:

pissa    	        2	      20480	  0.3125	   0.75  	  5.25 	  2.958	  43.66	6.124  	5.909	       0	outputs/qwen_train_probe/pissa_adapter.pt

Mixed. FP32 toy identity is consistent with paper. Qwen has id_err=0.3125, despite scripts/qwen_train_probe.py:26 forcing alpha=r; likely bf16 residual/SVD roundoff, but the log itself is not an identity pass in paper terms. The probe’s pass condition accepts this.

5. Bugs / concerns
   Potentially material bf16 initialization error on real weights: id_err=0.3125 is too large to treat as “paper identity” without a relative tolerance or logit-scale context. Save/load assumes loading into the same unmodified base model, because the residual is recomputed by attach() rather than saved. Missing test: PiSSA should explicitly check alpha != r fails or warns, since otherwise initial reconstruction is not faithful.

6. Confidence
   Medium — core math is right in FP32, but Qwen identity evidence is concerning and scaling fidelity depends on config.

---

dora

1. Paper claim summary
   DoRA (docs/papers/dora_2402.09353.txt §4.1, eq.5): decompose weight into magnitude and direction, initialize m = ||W0||c, V = W0, freeze V, and learn magnitude plus LoRA directional update W' = m (W0 + BA) / ||W0 + BA||c; LoRA init makes W' = W0 before fine-tuning.

2. What our code does — src/lora_lite/variants/dora.py:23, src/lora_lite/variants/dora.py:32, src/lora_lite/variants/dora.py:44

"lora_m": ParamSpec((d_out,), init="zeros", trainable=True),
col_norm = W.norm(dim=1).to(layer.lora_m.dtype)
BA = einsum(layer.lora_B, layer.lora_A, "o r, r i -> o i")
V = layer.weight + scale * BA
return (layer.lora_m / v_norm) * combined

3. Match? Y
   Faithful for plain nn.Linear, modulo PyTorch’s row-oriented weight convention. The implementation explicitly documents and enforces no bnb support.

4. Smoke evidence
   Toy row from logs/smoke.log:42-48:

=== variant=dora dtype=torch.float32 ===
  t=0 identity: max|y_adapt - y_base| = 0.000e+00  (base scale 4.609e+00)
  save/load: max|y_loaded - y_adapt| = 0.000e+00
  loss[0]=1.0882  loss[-1]=0.3996  drop=63.3%

bnb rows from logs/smoke.log:73,79:

Linear8bitLt   dora  : fail-loud OK (TypeError)
Linear4bit     dora  : fail-loud OK (TypeError)

Qwen row from logs/qwen_probe.log:20:

dora     	        2	      23552	  0     	   0.4062	  5.25 	  2.189	  58.3 	2.052  	7.734	       0	outputs/qwen_train_probe/dora_adapter.pt

Consistent with paper: identity at init, learns, reloads.

5. Bugs / concerns
   No obvious gradient-flow bug. Concern: paper discusses a cost-saving / gradient adjustment around the denominator; this code differentiates through v_norm. I would not call that wrong for eq.5, but it may differ from the final reported DoRA variant. Missing test: verify lora_m equals the correct orientation-specific norm for a nonsquare linear layer.

6. Confidence
   High — formula and initialization line up, and both toy and Qwen evidence support it.

---

ia3

1. Paper claim summary
   IA3 (docs/papers/ia3_2205.05638.txt §3): learn vectors that elementwise rescale activations, specifically keys, values, and FFN intermediate activations: lk ⊙ K, lv ⊙ V, and (lff ⊙ gamma(W1x))W2.

2. What our code does — src/lora_lite/variants/ia3.py:31, src/lora_lite/variants/ia3.py:39

return {"lora_g": ParamSpec((d_out,), init="ones", trainable=True)}
return y * layer.lora_g

3. Match? Partial
   The operation is IA3-style output gating, but target semantics are not paper-faithful by default. The docstring explicitly documents the deviation at src/lora_lite/variants/ia3.py:5-18. Qwen probe targets q_proj/v_proj, while paper IA3 would use k_proj/v_proj plus FFN intermediate.

4. Smoke evidence
   Toy row from logs/smoke.log:33-39:

=== variant=ia3 dtype=torch.float32 ===
  t=0 identity: max|y_adapt - y_base| = 0.000e+00  (base scale 4.609e+00)
  save/load: max|y_loaded - y_adapt| = 0.000e+00
  loss[0]=1.0823  loss[-1]=0.1228  drop=88.7%

bnb rows from logs/smoke.log:70,76:

Linear8bitLt   ia3   : identity_err=0.000e+00 grad_nonzero=True
Linear4bit     ia3   : identity_err=0.000e+00 grad_nonzero=True

Qwen row from logs/qwen_probe.log:19:

ia3      	        2	       3072	  0     	   0.375 	  5.25 	  4.473	  14.79	0.463  	5.926	       0	outputs/qwen_train_probe/ia3_adapter.pt

Numbers are consistent with identity-at-init activation scaling, but the smoke/probe do not validate paper-correct IA3 placement.

5. Bugs / concerns
   Main issue is target placement, not arithmetic. Missing test: attach IA3 with the recommended k_proj/v_proj/up_proj pattern and assert those exact targets, not q_proj/v_proj.

6. Confidence
   Medium — implementation is correct for a documented IA3-like general gate, not full paper IA3.

---

hra

1. Paper claim summary
   HRA (docs/papers/hra_2405.17484.txt §3.1, eqs.1-2): adapt a frozen matrix as z = W (prod_i H_i) x, where each Householder reflection is H_i = I - 2 u_i u_i^T with unit vectors. §3.4, eq.6 adds an orthogonality regularizer on the reflection vectors.

2. What our code does — src/lora_lite/variants/hra.py:33, src/lora_lite/variants/hra.py:46

"lora_U": ParamSpec((cfg.r, d_in), init="kaiming", trainable=True),
"lora_gate": ParamSpec((), init="zeros", trainable=True),
sq = (u * u).sum().clamp_min(1e-12)
Rx = Rx - coeff.unsqueeze(-1) * u
return x + layer.lora_gate * (Rx - x)

3. Match? Partial
   The Householder chain is recognizable and the omitted regularizer is documented in the docstring. But the scalar zero gate is not the paper’s forward: for gate != 1, x + gate*(Rx-x) is not a product of orthogonal Householder reflections. The identity-at-init deviation is documented, but it changes gradient flow.

4. Smoke evidence
   Toy row from logs/smoke.log:51-57:

=== variant=hra dtype=torch.float32 ===
  t=0 identity: max|y_adapt - y_base| = 0.000e+00  (base scale 4.609e+00)
  save/load: max|y_loaded - y_adapt| = 0.000e+00
  loss[0]=1.0882  loss[-1]=0.0305  drop=97.2%

bnb rows from logs/smoke.log:71,77:

Linear8bitLt   hra   : identity_err=0.000e+00 grad_nonzero=True
Linear4bit     hra   : identity_err=2.447e-04 grad_nonzero=True

Qwen row from logs/qwen_probe.log:21:

hra      	        2	       8194	  0     	   0.3594	  5.25 	  4.136	  21.23	0.09808	4.49 	       0	outputs/qwen_train_probe/hra_adapter.pt

Identity and learning pass. But grad_nonzero=True is insufficient: with lora_gate=0, gradients into lora_U are initially zero; the first update can only move the gate.

5. Bugs / concerns
   Gradient-flow concern: at initialization, return x + gate*(Rx-x) makes d output / d U proportional to gate, so lora_U has zero gradient when lora_gate=0. This is not caught by the logs. Paper regularizer is omitted and documented. The bnb 4-bit identity error 2.447e-04 passes a loose smoke tolerance but is not exact identity.

6. Confidence
   Medium-Low — smoke says it trains, but the zero-gate formulation is materially different from paper HRA and creates an initial dead-U step.

---

delora

1. Paper claim summary
   DeLoRA (docs/papers/delora_2503.18225.txt §2.2, eq.15): learn normalized low-rank BΞA and scale lambda * ||W|| / r, decoupling angular learning from adaptation strength. The paper says initialization preserves the pretrained model by merging a frozen copy of the initialized adaptation matrices, not by simply zeroing the scale.

2. What our code does — src/lora_lite/variants/delora.py:30, src/lora_lite/variants/delora.py:43, src/lora_lite/variants/delora.py:52

"lora_A": ParamSpec((cfg.r, d_in), init="kaiming", trainable=True),
"lora_B": ParamSpec((d_out, cfg.r), init="kaiming", trainable=True),
"lora_lambda": ParamSpec((), init=lambda t: t.fill_(lam0), trainable=True)
A = F.normalize(layer.lora_A, dim=1)
scale = layer.lora_lambda * layer.lora_wnorm / cfg.r

3. Match? Partial
   The normalized update and ||W||/r scaling match eq.15. The initialization does not match the paper’s Eq.9-style pretrained-preserving frozen-copy construction; instead it defaults lambda0=0 for identity. This is partially documented in the docstring, but the docstring understates the paper’s frozen-copy initialization.

4. Smoke evidence
   Toy row from logs/smoke.log:24-30:

=== variant=delora dtype=torch.float32 ===
  t=0 identity: max|y_adapt - y_base| = 0.000e+00  (base scale 4.609e+00)
  save/load: max|y_loaded - y_adapt| = 0.000e+00
  loss[0]=1.0909  loss[-1]=0.0277  drop=97.5%

bnb rows from logs/smoke.log:69,75:

Linear8bitLt   delora: identity_err=0.000e+00 grad_nonzero=True
Linear4bit     delora: identity_err=0.000e+00 grad_nonzero=True

Qwen row from logs/qwen_probe.log:18:

delora   	        2	      20484	  0.7188	   0.4688	  5.236	  3.364	  35.75	2.143  	9.086	       0	outputs/qwen_train_probe/delora_adapter.pt

Not consistent with the stated expectation that DeLoRA should be identity at t=0: Qwen uses variant_kwargs={"lambda0": 0.1} in scripts/qwen_train_probe.py:31, so id_err=0.7188 is expected from this implementation but not a paper-faithful pretrained initialization.

5. Bugs / concerns
   Major gradient-flow/design concern: with default lambda0=0, A and B receive zero gradient initially because the update is multiplied by zero; only lambda moves on the first step. With nonzero lambda0, training gradients flow, but identity is broken. The paper’s frozen-copy initialization is the way to get both nonzero scale and pretrained identity; this implementation lacks it. Missing tests: explicit per-parameter gradient check at lambda0=0, and identity check for the nonzero-lambda training config.

6. Confidence
   Medium — eq.15 forward is mostly present, but initialization is not paper-faithful and Qwen evidence exposes the tradeoff.

---

Aggregate

variant	paper match	smoke pass	qwen pass	bugs found	confidence
lora	Y	Y	Y	none material	High
pissa	Partial	Y	Partial	bf16/Qwen init error; config-sensitive alpha==r; residual not saved	Medium
dora	Y	Y	Y	possible denominator-gradient variant mismatch	High
ia3	Partial	Y	Partial	target placement not paper IA3; missing exact-placement test	Medium
hra	Partial	Y	Partial	zero gate gives initial zero grad to U; not orthogonal for gate != 1	Medium-Low
delora	Partial	Y	N/Partial	no Eq.9 frozen-copy init; zero-lambda dead A/B first step; nonzero-lambda breaks identity	Medium

Biggest Risks

• Initialization vs gradient-flow tradeoffs are being hidden by coarse tests: HRA’s U and DeLoRA’s A/B can be initially dead while grad_nonzero=True still passes.
• Qwen probe pass criteria do not enforce paper identity: PiSSA and DeLoRA show large id_err rows but the log still says pass.
• Target semantics are under-tested: IA3’s paper-specific k/v/ffn placement is documented as a deviation, but the real-model probe uses q/v, so it does not validate IA3 faithfulness.

[done] end_turn