Update model_api.py

model_api.py

@@ -1,22 +1,6 @@
-from huggingface_hub import InferenceClient
-import os
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 
-def query_model(prompt):
-
-    HF_TOKEN = os.getenv("HF_TOKEN")
-
-    client = InferenceClient(
-        model="microsoft/Phi-3-mini-4k-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=1500,
-        temperature=0.7
-    )
-
-    return response.choices[0].message.content
+def load_model():
+    tokenizer = AutoTokenizer.from_pretrained("google/flan-t5-base")
+    model = AutoModelForSeq2SeqLM.from_pretrained("google/flan-t5-base")
+    return tokenizer, model