chore(release): v0.2.0 — AWQ Option B + 8-bit embed_tokens

Bump lumen-app + frontend + tauri to 0.2.0.

What ships:
- `hsng95/gemma-4-26b-a4b-mlx-imatrix3plus-awq` as the default Gemma 4
  catalog entry (12 GB, 3.916 bpw). Multi-seed mean PPL 16.2 ppl
  better than the no-AWQ imatrix3plus baseline AND decode is faster
  than uniform 4-bit on M3 Max (73 vs 71 tok/s).
- bf16 / mixed-precision embed_tokens support in the Gemma 4 native
  loader. Future skip-list quant builds will no longer trip the
  "missing embed_tokens.scales" load error.
- Full AWQ tooling under scripts/quant/ (awq_search, awq_apply,
  awq_filter_scales, test_awq_apply_parity, test_long_context_extended).

Upgrade path: lumen-app's HF Hub revision tracking detects the new
commit on the same repo id, prompts Update on the MODELS card. The
old v0.1.3 download (still at the bf16-embed revision) will be
replaced in-place by the 8-bit-embed ship build.

Author: rabbitson87

Cargo.lock

@@ -1,6 +1,6 @@
 [package]
 name = "lumen-app"
-version = "0.1.3"
+version = "0.2.0"
 edition.workspace = true
 rust-version.workspace = true
 license.workspace = true

crates/lumen-app/Cargo.toml

@@ -1,7 +1,7 @@
 {
   "name": "lumen-app-frontend",
   "private": true,
-  "version": "0.1.3",
+  "version": "0.2.0",
   "type": "module",
   "scripts": {
     "predev": "cargo build --manifest-path ../../../Cargo.toml -p lumen-server --release",

crates/lumen-app/frontend/package.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://schema.tauri.app/config/2",
   "productName": "Lumen",
-  "version": "0.1.3",
+  "version": "0.2.0",
   "identifier": "ai.lumen.app",
   "build": {
     "frontendDist": "frontend/dist",