Update main.py

main.py

@@ -1,24 +1,22 @@
-from ctransformers import AutoModelForCausalLM
+from llama_cpp import LlamaModel
 from fastapi import FastAPI
 from pydantic import BaseModel
 
+# Charger le modèle LLaMA
+llm = LlamaModel(model_path="phi-2.Q5_K_M.gguf")
 
-llm = AutoModelForCausalLM.from_pretrained("phi-2.Q5_K_M.gguf",
-model_type='pi',
-max_new_tokens = 1096,
-threads = 3,
-)
-
-#Pydantic object
-class validation(BaseModel):
+# Pydantic object
+class Validation(BaseModel):
     prompt: str
-#Fast API
+
+# 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"
-    return llm(prompt)
+    response = llm.generate(prompt, max_new_tokens=1096, num_threads=3)
+    return response