Upload 4 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+codellama-7b-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3.10
+
+WORKDIR /code
+
+COPY ./requirements.txt /code/requirements.txt
+
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+COPY ./codellama-7b-instruct.q4_K_M.gguf /code/codellama-7b-instruct.q4_K_M.gguf
+COPY ./main.py /code/main.py
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

codellama-7b-instruct.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0701500c591c2c1b910516658e58044cdfa07b2e8b5a2e3b6808d983441daf1a
+size 4081095360

main.py

@@ -0,0 +1,21 @@
+from ctransformers import AutoModelForCausalLM
+from fastapi import FastAPI
+from pydantic import BaseModel
+
+llm = AutoModelForCausalLM.from_pretrained("TheBloke/CodeLlama-7B-Instruct-GGUF", 
+                                           model_file="codellama-7b-instruct.q4_K_M.gguf", 
+                                           model_type="llama", 
+                                           gpu_layers=0)
+#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