Update main.py

main.py

@@ -1,22 +1,24 @@
-from llama_cpp import LlamaModel
+from ctransformers import AutoModelForCausalLM
 from fastapi import FastAPI
 from pydantic import BaseModel
 
-# Charger le modèle LLaMA
-llm = LlamaModel(model_path="phi-2.Q5_K_M.gguf")
 
-# Pydantic object
-class Validation(BaseModel):
-    prompt: str
+llm = AutoModelForCausalLM.from_pretrained("zephyr-7b-beta.Q4_K_S.gguf",
+model_type='mistral',
+max_new_tokens = 1096,
+threads = 3,
+)
 
-# Fast API
+#Pydantic object
+class validation(BaseModel):
+    prompt: str
+#Fast API
 app = FastAPI()
 
 @app.post("/llm_on_cpu")
-async def stream(item: Validation):
+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"
-    response = llm.generate(prompt, max_new_tokens=1096, num_threads=3)
-    return response
+    return llm(prompt)