Update app.py

app.py

@@ -27,14 +27,14 @@ cancel_event = threading.Event()
 # ------------------------------
 MODELS = {
     # ~30.5B total parameters (MoE: 3.3B activated)
-    "Qwen3-30B-A3B-Thinking-2507-FP8": {
-        "repo_id": "Qwen/Qwen3-30B-A3B-Thinking-2507-FP8",
-        "description": "FP8-quantized MoE model with 30.5B total parameters (3.3B activated), 128 experts (8 activated), 48 layers, and native 262,144-token context. Optimized for complex reasoning tasks with enhanced thinking capabilities in mathematics, coding, science, and agent benchmarks. Supports only thinking mode; includes automatic reasoning delimiters."
-    },
-    "Qwen3-30B-A3B-Instruct-2507-FP8": {
-        "repo_id": "Qwen/Qwen3-30B-A3B-Instruct-2507-FP8",
-        "description": "FP8-quantized instruct-tuned variant of Qwen3-30B-A3B (30.5B total params, 3.3B activated), featuring strong general capabilities in instruction following, tool usage, text generation, and 256K long-context understanding. Ideal for agentic and multi-turn dialogue applications."
-    },
+    # "Qwen3-30B-A3B-Thinking-2507-FP8": {
+    #     "repo_id": "Qwen/Qwen3-30B-A3B-Thinking-2507-FP8",
+    #     "description": "FP8-quantized MoE model with 30.5B total parameters (3.3B activated), 128 experts (8 activated), 48 layers, and native 262,144-token context. Optimized for complex reasoning tasks with enhanced thinking capabilities in mathematics, coding, science, and agent benchmarks. Supports only thinking mode; includes automatic reasoning delimiters."
+    # },
+    # "Qwen3-30B-A3B-Instruct-2507-FP8": {
+    #     "repo_id": "Qwen/Qwen3-30B-A3B-Instruct-2507-FP8",
+    #     "description": "FP8-quantized instruct-tuned variant of Qwen3-30B-A3B (30.5B total params, 3.3B activated), featuring strong general capabilities in instruction following, tool usage, text generation, and 256K long-context understanding. Ideal for agentic and multi-turn dialogue applications."
+    # },
 
     # ~235B total parameters (MoE: 22B activated) — included for reference if added later
     # "Qwen3-235B-A22B-Thinking": { ... },
@@ -95,10 +95,10 @@ MODELS = {
     },
 
     # ~3B
-    "AI21-Jamba-Reasoning-3B": {
-        "repo_id": "ai21labs/AI21-Jamba-Reasoning-3B",
-        "description": "A compact 3B hybrid Transformer–Mamba reasoning model with 256K context length, strong intelligence benchmark scores (61% MMLU-Pro, 52% IFBench), and efficient inference suitable for edge and datacenter use. Outperforms Gemma-3 4B and Llama-3.2 3B despite smaller size."
-    },
+    # "AI21-Jamba-Reasoning-3B": {
+    #     "repo_id": "ai21labs/AI21-Jamba-Reasoning-3B",
+    #     "description": "A compact 3B hybrid Transformer–Mamba reasoning model with 256K context length, strong intelligence benchmark scores (61% MMLU-Pro, 52% IFBench), and efficient inference suitable for edge and datacenter use. Outperforms Gemma-3 4B and Llama-3.2 3B despite smaller size."
+    # },
     "Qwen2.5-Taiwan-3B-Reason-GRPO": {
         "repo_id": "benchang1110/Qwen2.5-Taiwan-3B-Reason-GRPO",
         "description": "Qwen2.5-Taiwan model with 3 B parameters, Reason-GRPO fine-tuned"