Upload 3 files

Dockerfile

@@ -0,0 +1,20 @@
+FROM python:3.10
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+RUN useradd user
+
+USER user
+
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:${PATH}
+
+WORKDIR $HOME/app
+
+COPY --chown=user . $HOME/app
+
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,26 @@
+from fastapi import FastAPI
+from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel, PeftConfig
+
+# Initialize FastAPI app
+app = FastAPI()
+
+# Load PEFT model configuration and base model
+config = PeftConfig.from_pretrained("frankmorales2020/Mistral-7B-text-to-sql-flash-attention-2-dataeval")
+base_model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3")
+model = PeftModel.from_pretrained(base_model, "frankmorales2020/Mistral-7B-text-to-sql-flash-attention-2-dataeval")
+
+# Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3")
+
+# Create the pipeline
+pipe = pipeline("text2sql", model=model, tokenizer=tokenizer)
+
+@app.get("/")
+def home():
+    return {"message": "Hello World"}
+
+@app.get("/generate")
+def generate(text: str):
+    output = pipe(text)
+    return {"output": output[0]['generated_text']}

requirements.txt

@@ -0,0 +1,8 @@
+fastapi==0.74.*
+requests==2.27.*
+uvicorn[standard]==0.17.*
+sentencepiece==0.1.*
+torch>=1.13.0
+transformers==4.*
+numpy<2
+peft==0.11.1