Sync space files (2026-04-05)

Rebuild: settings+new-chat visible in chat header

Fix: move Vexorium header into ChatApp, restore settings+new-chat visibility

Fix: move Vexorium header into ChatApp, restore settings+new-chat visibility

Rebuild: fix browser cache persistence

Fix cache: remove cache_dir override so env.useBrowserCache=true actually works

Rebuild: settings panel + updated examples + Vexorium style

Restore settings panel + Vexorium style: src/model-config.ts

Restore settings panel + Vexorium style: src/components/ChatApp.tsx

Rebuild: header Vexorium logo, right Nemotron image

Simplify logo layout: header Vexorium, right Nemotron only

Simplify logo layout: header Vexorium, right Nemotron only

Rebuild dist/: Nemotron × Vexorium logo

Add Nemotron × Vexorium logo composition

Rebuild dist/ with Vexorium brand style

Add Vexorium logo SVG

Vexorium brand: update src/components/FeatureCard.tsx

Vexorium brand: update src/components/AppShell.tsx

Vexorium brand: update src/components/LandingPage.tsx

Vexorium brand: update src/App.tsx

Vexorium brand: update src/index.css

Rebuild dist/ with grpo-v21 model ID

Switch model to bobber/lex-interviewer-nemotron-4b-grpo-v21

add back test-webgpu.html to dist

revert to 9b50a208 + modelId only, thinking enabled

deploy: fine-tuned model with thinking disabled (Q4 thinking broken on WebGPU)

fix: adapter.requestAdapterInfo() not available in all browsers

fix: use explicit ESM path for transformers.js CDN import

fix: move test page to dist/ so static Space can serve it

add: WebGPU test page at /test-webgpu.html

revert: back to 9b50a208 (reference model, known working)

fix: handle Q4 model missing </think> on WebGPU

test: 9b50a208 code + only modelId changed to fine-tuned model

revert: back to 9b50a208 (reference model) for testing

fix: MessageBubble falls back to reasoning when content is empty — eliminates 'No response'

debug: add FINAL console.log to trace parser state — must find root cause

fix: when model skips </think>, move reasoning to content and clear reasoning

fix: extract last question from reasoning when model stops after </think> without content

fix: remove cache_dir override — use default browser Cache API for ONNX persistence

fix: handle missing </think> — fallback reasoning to content, never show 'No response'

debug: add console logging to diagnose 'No response' issue

fix: explicit eos_token_id=[2,11] at generation time — works even with cached model config

fix: revert to reference streamer approach + fix eos_token_id in model config

fix: filter special tokens and trailing whitespace from stream output

test: float-only patch — base q4 weights + fine-tuned layernorms/biases

test: use reference base model to verify pipeline works

fix: remove ort-web override — model ONNX now has single external data file

fix: transformers.js 4.0.0-next.8 + ort-web 1.16.3 — fixes both nemotron_h and MountedFiles errors

fix: pin ort-web to 1.16.3 to fix Module.MountedFiles error with q4 ONNX external data

Revert to dtype=q4 — model_q4.onnx now available in our repo