v0.8.5-fix: spec-decode examples → open-weight pairs (HF auth not required)

Bug report from user: clicking the "good example" button returned
"Target: model is gated or private (HTTP 401)". Llama-3.1 needs Meta
license acceptance + HF login, which a public browser fetch cannot
satisfy.

Switched both default examples to OPEN-WEIGHT models that 200 from a
non-authenticated request:
- Good (compatible): Qwen/Qwen2.5-72B-Instruct + Qwen/Qwen2.5-7B-Instruct
- Bad (incompatible): Qwen/Qwen2.5-7B-Instruct + microsoft/Phi-3.5-mini-instruct

Verified all three tokenizer.json URLs return 200 via curl.

Added an inline note ("💡 Gated models require HF login...") under the
input fields so users learn why Llama/Mistral/Gemma fail and which
families work without auth (Qwen/Phi/DeepSeek/Yi/StarCoder/Falcon).
4-lang i18n added (EN/ES/FR/ZH).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

index.html

@@ -1125,17 +1125,20 @@
       </p>
       <div class="form-row">
         <label for="spec-target-id" data-i18n="speculative.target_label">Target (large) model id:</label>
-        <input type="text" id="spec-target-id" placeholder="meta-llama/Llama-3.1-70B-Instruct" style="flex:1;" />
+        <input type="text" id="spec-target-id" placeholder="Qwen/Qwen2.5-72B-Instruct" style="flex:1;" />
       </div>
       <div class="form-row">
         <label for="spec-draft-id" data-i18n="speculative.draft_label">Draft (small) model id:</label>
-        <input type="text" id="spec-draft-id" placeholder="meta-llama/Llama-3.1-8B-Instruct" style="flex:1;" />
+        <input type="text" id="spec-draft-id" placeholder="Qwen/Qwen2.5-7B-Instruct" style="flex:1;" />
       </div>
       <div class="form-row">
         <button type="button" id="spec-check-btn" data-i18n="speculative.check_btn">🔍 Check compatibility</button>
-        <button type="button" id="spec-example-good-btn" class="secondary" data-i18n="speculative.example_good_btn">↳ Example: Llama-3.1 8B/70B (good)</button>
+        <button type="button" id="spec-example-good-btn" class="secondary" data-i18n="speculative.example_good_btn">↳ Example: Qwen2.5 7B/72B (good)</button>
         <button type="button" id="spec-example-bad-btn" class="secondary" data-i18n="speculative.example_bad_btn">↳ Example: cross-family (bad)</button>
       </div>
+      <p class="recipe-desc subtle" style="font-size:0.82em;" data-i18n="speculative.gated_note">
+        💡 <strong>Gated models</strong> (Llama, Mistral, Gemma) require HF login + license acceptance — this tool can't auth, so they return 401. Use open-weight pairs (Qwen, Phi, DeepSeek, Yi, StarCoder, Falcon) for demos.
+      </p>
       <p id="spec-status" class="recipe-desc" style="font-size:0.92em;"></p>
       <div id="spec-output" style="margin-top: 1em;"></div>
     </section>

js/i18n.js

@@ -648,8 +648,9 @@ export const TRANSLATIONS = {
     "speculative.target_label_short": "target",
     "speculative.draft_label_short":  "draft",
     "speculative.check_btn":       "🔍 Check compatibility",
-    "speculative.example_good_btn":"↳ Example: Llama-3.1 8B/70B (good)",
+    "speculative.example_good_btn":"↳ Example: Qwen2.5 7B/72B (good)",
     "speculative.example_bad_btn": "↳ Example: cross-family (bad)",
+    "speculative.gated_note":      "💡 <strong>Gated models</strong> (Llama, Mistral, Gemma) require HF login + license acceptance — this tool can't auth, so they return 401. Use open-weight pairs (Qwen, Phi, DeepSeek, Yi, StarCoder, Falcon) for demos.",
     "speculative.status.fetching": "🔄 Fetching tokenizer.json from HF Hub for both models…",
     "speculative.status.done":     "✅ {verdict}",
     "speculative.status.error":    "❌ Error",
@@ -1801,8 +1802,9 @@ export const TRANSLATIONS = {
     "speculative.target_label_short": "target",
     "speculative.draft_label_short":  "draft",
     "speculative.check_btn":       "🔍 Verificar compatibilidad",
-    "speculative.example_good_btn":"↳ Ejemplo: Llama-3.1 8B/70B (bueno)",
+    "speculative.example_good_btn":"↳ Ejemplo: Qwen2.5 7B/72B (bueno)",
     "speculative.example_bad_btn": "↳ Ejemplo: cross-family (malo)",
+    "speculative.gated_note":      "💡 <strong>Modelos gated</strong> (Llama, Mistral, Gemma) requieren login HF + aceptar licencia — esta tool no puede autenticar, así que devuelven 401. Usa pares open-weight (Qwen, Phi, DeepSeek, Yi, StarCoder, Falcon) para demos.",
     "speculative.status.fetching": "🔄 Haciendo fetch de tokenizer.json desde HF Hub para ambos modelos…",
     "speculative.status.done":     "✅ {verdict}",
     "speculative.status.error":    "❌ Error",
@@ -2818,8 +2820,9 @@ export const TRANSLATIONS = {
     "speculative.target_label_short": "target",
     "speculative.draft_label_short":  "draft",
     "speculative.check_btn":       "🔍 Vérifier compatibilité",
-    "speculative.example_good_btn":"↳ Exemple : Llama-3.1 8B/70B (bon)",
+    "speculative.example_good_btn":"↳ Exemple : Qwen2.5 7B/72B (bon)",
     "speculative.example_bad_btn": "↳ Exemple : cross-family (mauvais)",
+    "speculative.gated_note":      "💡 <strong>Modèles gated</strong> (Llama, Mistral, Gemma) requièrent login HF + acceptation de licence — cet outil ne peut pas auth, ils renvoient 401. Utilisez des paires open-weight (Qwen, Phi, DeepSeek, Yi, StarCoder, Falcon) pour les démos.",
     "speculative.status.fetching": "🔄 Récupération de tokenizer.json depuis HF Hub pour les deux modèles…",
     "speculative.status.done":     "✅ {verdict}",
     "speculative.status.error":    "❌ Erreur",
@@ -3835,8 +3838,9 @@ export const TRANSLATIONS = {
     "speculative.target_label_short": "target",
     "speculative.draft_label_short":  "draft",
     "speculative.check_btn":       "🔍 检查兼容性",
-    "speculative.example_good_btn":"↳ 示例：Llama-3.1 8B/70B（好）",
+    "speculative.example_good_btn":"↳ 示例：Qwen2.5 7B/72B（好）",
     "speculative.example_bad_btn": "↳ 示例：跨 family（坏）",
+    "speculative.gated_note":      "💡 <strong>受限模型</strong>（Llama、Mistral、Gemma）需要 HF 登录 + 接受许可——这个工具无法 auth，所以会返回 401。请使用 open-weight 对（Qwen、Phi、DeepSeek、Yi、StarCoder、Falcon）作为演示。",
     "speculative.status.fetching": "🔄 从 HF Hub 获取两个模型的 tokenizer.json…",
     "speculative.status.done":     "✅ {verdict}",
     "speculative.status.error":    "❌ 错误",

js/main.js

@@ -4072,14 +4072,18 @@ async function runSpecCheck() {
 }
 
 $("spec-check-btn")?.addEventListener("click", runSpecCheck);
+// Examples use OPEN-WEIGHT models (no HF gating). Llama / Mistral /
+// Gemma require license acceptance — they 401 from a public browser
+// fetch. Qwen2.5 + Phi-3.5 ship under permissive licenses so the
+// in-app demo Just Works without the user having to log in to HF.
 $("spec-example-good-btn")?.addEventListener("click", () => {
-  $("spec-target-id").value = "meta-llama/Llama-3.1-70B-Instruct";
-  $("spec-draft-id").value  = "meta-llama/Llama-3.1-8B-Instruct";
+  $("spec-target-id").value = "Qwen/Qwen2.5-72B-Instruct";
+  $("spec-draft-id").value  = "Qwen/Qwen2.5-7B-Instruct";
   runSpecCheck();
 });
 $("spec-example-bad-btn")?.addEventListener("click", () => {
-  $("spec-target-id").value = "meta-llama/Llama-3.1-8B-Instruct";
-  $("spec-draft-id").value  = "mistralai/Mistral-7B-Instruct-v0.3";
+  $("spec-target-id").value = "Qwen/Qwen2.5-7B-Instruct";
+  $("spec-draft-id").value  = "microsoft/Phi-3.5-mini-instruct";
   runSpecCheck();
 });