Update model_loader.py

model_loader.py

@@ -1,6 +1,25 @@
-from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+from huggingface_hub import InferenceClient
+import os
 
-def load_model():
-    tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-base")
-    model = AutoModelForSeq2SeqLM.from_pretrained("google/flan-t5-base")
-    return tokenizer, model
+def query_model(prompt):
+    try:
+        HF_TOKEN = os.getenv("HF_TOKENN")
+
+        client = InferenceClient(
+            model="Qwen/Qwen2.5-7B-Instruct",
+            token=HF_TOKEN
+        )
+
+        response = client.chat_completion(
+            messages=[
+                {"role": "system", "content": "You are a certified professional fitness trainer."},
+                {"role": "user", "content": prompt}
+            ],
+            max_tokens=2000,
+            temperature=0.7
+        )
+
+        return response.choices[0].message.content
+
+    except Exception as e:
+        return f"Error: {str(e)}"