Delete DeployingModel

DeployingModel/Dockerfile

@@ -1,12 +0,0 @@
-FROM python:3.9
-
-WORKDIR /code
-
-COPY ./requirements.txt /code/requirements.txt
-
-RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
-
-COPY ./zephyr-7b-beta.Q4_K_S.gguf /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"]

DeployingModel/main.py

@@ -1,24 +0,0 @@
-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)

DeployingModel/requirements.txt

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

DeployingModel/zephyr-7b-beta.Q4_K_S.gguf

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cafa0b85b2efc15ca33023f3b87f8d0c44ddcace16b3fb608280e0eb8f425cb1
-size 4140373696