feat: Add GLM-4.7-Flash-REAP-23B model with community settings

- Added glm_4_7_flash_reap_23b from unsloth
- Uses TQ1_0 quantization (6.54 GB)
- Community-suggested settings:
- temperature: 0.6
- top_p: 0.95
- top_k: 20
- repeat_penalty: 1.05
- 128K context window (capped at 32K for HF)

app.py

@@ -218,6 +218,20 @@ AVAILABLE_MODELS = {
             "repeat_penalty": 1.1,
         },
     },
+    "glm_4_7_flash_reap_23b": {
+        "name": "GLM-4.7-Flash-REAP-23B Thinking (128K Context)",
+        "repo_id": "unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF",
+        "filename": "*TQ1_0.gguf",
+        "max_context": 131072,
+        "default_temperature": 0.6,
+        "supports_toggle": False,
+        "inference_settings": {
+            "temperature": 0.6,
+            "top_p": 0.95,
+            "top_k": 20,
+            "repeat_penalty": 1.05,
+        },
+    },
 }
 
 DEFAULT_MODEL_KEY = "qwen3_600m_q4"