Upload 3 files

Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3.12-slim
+
+RUN apt-get update && apt-get install -y git
+
+WORKDIR /app
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY app.py .
+
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,41 @@
+from fastapi import FastApi, Request
+from pydantic import BaseModel
+from transformers import pipeline, AutoTokenizer, AutoModelForSeq2SeqLM
+from fastapi.middleware import CORSMiddleware
+
+app = FastApi()
+
+app.add_middleware(
+   CORSMiddleware,
+   allow_origins=["*"],
+   allow_methods=["*"],
+   allow_methods=["*"],
+)
+
+model_name = "pszemraj/long-t5-tglobal-base-16384-book-summary"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+
+class InputText(BaseModel):
+   text: str
+
+@app.post("/summarize")
+async def summarize(input: InputText):
+   inputs = tokenizer(
+      input.text,
+      return_tensors="pt",
+      max_length=16384,
+      truncation=True,
+   )
+
+   summary_ids = model.generate(
+      inputs["input_ids"],
+      max_length=1024,
+      min_length=50,
+      length_penalty=2.0,
+      num_beams=4,
+      early_stopping=True,
+   )
+
+   summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
+   return summary

requirements.txt

@@ -0,0 +1,5 @@
+fastapi
+uvicorn
+transformers
+torch
+accelerate