Create model_loader.py

model_loader.py

@@ -0,0 +1,22 @@
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+from config import HF_TOKEN, MODEL_ID
+
+def load_model():
+    tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, token=HF_TOKEN, trust_remote_code=True)
+    model = AutoModelForCausalLM.from_pretrained(
+        MODEL_ID,
+        token=HF_TOKEN,
+        trust_remote_code=True,
+        device_map="cpu",
+        torch_dtype=torch.float32,
+        low_cpu_mem_usage=True
+    )
+    return pipeline(
+        "text-generation",
+        model=model,
+        tokenizer=tokenizer,
+        max_new_tokens=100,
+        do_sample=True,
+        temperature=0.7,
+    )