Update app/llm.py

app/llm.py

@@ -32,7 +32,7 @@ class ChatModel(BaseModel):
 llm_chat = llama_cpp.Llama.from_pretrained(
     repo_id="moriire/healthcare-GGUF",
     filename="healthcare-GGUF-unsloth.Q4_K_M.gguf",
-    tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("moriire/healthcare-ai-adapter-merged"),
+    #tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("moriire/healthcare-ai-adapter-merged"),
     verbose=False,
      n_ctx=1024,
      n_gpu_layers=0,
@@ -41,7 +41,7 @@ llm_chat = llama_cpp.Llama.from_pretrained(
 llm_generate = llama_cpp.Llama.from_pretrained(
     repo_id="moriire/healthcare-GGUF",
     filename="healthcare-GGUF-unsloth.Q4_K_M.gguf",
-    tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("moriire/healthcare-ai-adapter-merged"),
+    #tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("moriire/healthcare-ai-adapter-merged"),
     verbose=False,
      n_ctx=4096,
      n_gpu_layers=0,
@@ -99,7 +99,7 @@ async def chat(chatm:ChatModel):#, user: schemas.BaseUser = fastapi.Depends(curr
 
 # Chat Completion API
 @llm_router.post("/generate", tags=["llm"])
-async def generate(gen:GenModel, user: schemas.BaseUser = fastapi.Depends(current_active_user)):
+async def generate(gen:GenModel)#, user: schemas.BaseUser = fastapi.Depends(current_active_user)):
     gen.system = "You are an helpful medical AI assistant."
     gen.temperature = 0.5
     gen.seed = 42