First commit

Dockerfile

@@ -0,0 +1,13 @@
+FROM python:3.10
+
+WORKDIR /app
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+# Make the script executable
+RUN chmod +x run.sh
+
+CMD ["bash", "run.sh"]

app/api.py

@@ -0,0 +1,14 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+from app.model import model
+
+app = FastAPI()
+
+class PromptRequest(BaseModel):
+    prompt: str
+    max_length: int = 256
+
+@app.post("/generate")
+async def generate_text(request: PromptRequest):
+    result = model.generate(request.prompt, request.max_length)
+    return {"response": result}

app/config.py

@@ -0,0 +1,5 @@
+import os
+
+MODEL_NAME = "deepseek-ai/deepseek-llm-r1-7b"
+HF_TOKEN = os.getenv("HF_TOKEN")  # Set this in the Hugging Face environment
+DEVICE = "cuda"  # Change to "cpu" if no GPU

app/model.py

@@ -0,0 +1,18 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+from app.config import MODEL_NAME, DEVICE
+
+class DeepSeekModel:
+    def __init__(self):
+        self.tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, token=os.getenv("HF_TOKEN"))
+        self.model = AutoModelForCausalLM.from_pretrained(
+            MODEL_NAME, torch_dtype=torch.float16, device_map="auto"
+        )
+
+    def generate(self, prompt, max_length=256):
+        inputs = self.tokenizer(prompt, return_tensors="pt").to(DEVICE)
+        with torch.no_grad():
+            outputs = self.model.generate(**inputs, max_length=max_length)
+        return self.tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+model = DeepSeekModel()

app/requirements.txt

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

run.sh

@@ -0,0 +1,2 @@
+#!/bin/bash
+uvicorn app.api:app --host 0.0.0.0 --port 8000 --workers 1