Create software_engineer_agent.py

agents/software_engineer_agent.py

@@ -0,0 +1,14 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+MODEL_REPO = "Rahul-8799/software_engineer_mellum"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_REPO, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(MODEL_REPO, torch_dtype=torch.float16, device_map="auto")
+model.eval()
+
+def run(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+    with torch.no_grad():
+        outputs = model.generate(**inputs, max_new_tokens=512)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)