First model version

main.py

@@ -1,21 +1,18 @@
-from ctransformers import AutoModelForCausalLM
+from llama_cpp import Llama
 from fastapi import FastAPI
 from pydantic import BaseModel
 
-file_name = "zephyr-7b-beta.Q4_K_S.gguf"
-llm = AutoModelForCausalLM.from_pretrained(file_name,
-    model_type='mistral',
-    max_new_tokens = 1096,
-    threads = 3,
-)
+model_file = "zephyr-7b-beta.Q4_K_S.gguf"
+llm = Llama(model_path=model_file, n_ctx=512, n_batch=126)
+
 
-#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.'
@@ -23,4 +20,4 @@ async def stream(item: validation):
     user, assistant = "<|user|>", "<|assistant|>"
     prompt = f"{system_prompt}{E_INST}\n{user}\n{item.prompt}{E_INST}\n{assistant}\n"
 
-    return llm(prompt)
+    return llm("What is an LLM?", max_tokens=100)

requirements.txt

@@ -5,4 +5,4 @@ uvicorn
 requests
 python-dotenv
 ctransformers
-huggingface-hub
+llama-cpp-python