Switch to Qwen2.5-7B-Instruct with hf-inference provider for text generation

config/models.yaml

@@ -1,10 +1,10 @@
 models:
-  # Qwen Model with Together Provider
-  - name: "Qwen3-Next-80B"
-    provider: "together"
-    model_id: "Qwen/Qwen3-Next-80B-A3B-Instruct"
+  # Qwen2.5-7B-Instruct with HF Inference Provider
+  - name: "Qwen2.5-7B-Instruct"
+    provider: "hf-inference"
+    model_id: "Qwen/Qwen2.5-7B-Instruct"
     params:
       max_new_tokens: 256
       temperature: 0.1
       top_p: 0.9
-    description: "Qwen3-Next-80B - Advanced instruction-following model via Together AI"
+    description: "Qwen2.5-7B-Instruct - Instruction-following model for text generation"