app.py

from transformers import AutoModelForCausalLM, AutoTokenizer
from fastapi import FastAPI

app = FastAPI()



@app
.get("/")
def greet_json():
model_name = "Qwen/QwQ-32B-Preview"

model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "How many r in strawberry."
messages = [
{"role": "system", "content": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step."},
{"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
**model_inputs,
max_new_tokens=512
)
generated_ids = [
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
return response

requirements.txt

@@ -0,0 +1,7 @@
+python-multipart
+fastapi
+pydantic
+uvicorn
+requests
+python-dotenv
+ctransformers