first commit

app.py

@@ -0,0 +1,28 @@
+from fastapi import FastAPI
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+app = FastAPI()
+
+# Load Qwen-7B once saat startup
+model_name = "Qwen/Qwen-7B"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="cpu")
+
+@app.get("/")
+def home():
+    return {"status": "ok", "message": "Qwen-7B API is running!"}
+
+@app.post("/chat")
+async def chat(prompt: str):
+    inputs = tokenizer(prompt, return_tensors="pt")
+    with torch.no_grad():
+        outputs = model.generate(
+            **inputs,
+            max_new_tokens=200,
+            do_sample=True,
+            temperature=0.7,
+            top_p=0.9
+        )
+    text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return {"response": text}

requirements.txt

@@ -0,0 +1,4 @@
+transformers>=4.40.0
+torch
+fastapi
+uvicorn