Upload 3 files

Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.9
+
+WORKDIR /app
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+RUN useradd -m user
+USER user
+
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+
+COPY --chown=user:user . .
+
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,42 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+import uvicorn
+from fastapi.middleware.cors import CORSMiddleware
+
+app = FastAPI()
+
+# Add CORS middleware
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # Allows all origins
+    allow_credentials=True,
+    allow_methods=["*"],  # Allows all methods
+    allow_headers=["*"],  # Allows all headers
+)
+
+# Initialize the model and tokenizer
+model_name = "bigscience/mt0-base"
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+class GenerationRequest(BaseModel):
+    prompt: str
+    max_tokens: int = 100
+
+@app.post("/generate")
+async def generate(request: GenerationRequest):
+    inputs = tokenizer(request.prompt, return_tensors="pt", padding=True, truncation=True)
+    
+    # Move inputs to the same device as the model
+    device = model.device
+    inputs = {k: v.to(device) for k, v in inputs.items()}
+    
+    outputs = model.generate(**inputs, max_new_tokens=request.max_tokens)
+    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return {"generated_text": generated_text}
+
+@app.get("/")
+def home():
+    return {"message": "Welcome to the Text Generation API"}
+

requirements.txt

@@ -0,0 +1,6 @@
+fastapi
+nest_asyncio
+uvicorn 
+pydantic 
+transformers 
+torch