Verify all variants on bnb 4bit/8bit; HRA paper-faithful rewrite

- Test all 6 variants against bnb.Linear8bitLt + Linear4bit in smoke
- bnb-friendly (LoRA, IA3, HRA, DeLoRA): identity err <= 2.4e-4
- bnb-incompatible (PiSSA, DoRA): fail-loud TypeError as expected
- HRA: rewrite to paper-faithful input-side reflections (h <- (I-2vv^T)h),
  fixing previous broken output-side formulation
- IA3: bypass dtype upcast for bnb (params stay fp16/quantized)
- DeLoRA: explicit type check rejecting non-nn.Linear (incl. bnb)
- adapter: special-case bnb param assignment via .data
- Re-verified Qwen0.6B HRA probe: drop=20.7%, id_err=0, reload=0

src/lora_lite/variants/lora.py

@@ -1,4 +1,9 @@
-"""Vanilla LoRA. Reference variant. y = Wx + (alpha/r) * B @ A @ x."""
+"""Vanilla LoRA. Hu et al. 2021  https://arxiv.org/abs/2106.09685
+
+    h = W x + (alpha/r) B A x
+
+Identity at t=0 from B=0. Faithful to the paper.
+"""
 from einops import einsum
 from torch import nn
 import torch