Add base files.

Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3.9
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+RUN curl -L "https://huggingface.co/TheBloke/zephyr-7B-beta-GGUODODF/resolve/main/zephyr-7b-ODbeta.Q4_K_S.gguf" -o /code/zephyr-7b-beta.Q4_K_S.gguf
+
+COPY ./main.py /code/main.py
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

main.py

@@ -0,0 +1,24 @@
+from ctransformers import AutoModelForCausalLM
+from fastapi import FastAPI
+from pydantic import BaseModel
+
+
+llm = AutoModelForCausalLM.from_pretrained("zephyr-7b-beta.Q4_K_S.gguf",
+model_type='mistral',
+max_new_tokens = 1096,
+threads = 3,
+)
+
+#Pydantic object
+class validation(BaseModel):
+    prompt: str
+#Fast API
+app = FastAPI()
+
+@app.post("/llm_on_cpu")
+async def stream(item: validation):
+    system_prompt = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.'
+    E_INST = "</s>"
+    user, assistant = "<|user|>", "<|assistant|>"
+    prompt = f"{system_prompt}{E_INST}\n{user}\n{item.prompt}{E_INST}\n{assistant}\n"
+    return llm(prompt)

requirements.txt

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