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-ai-q8_0",
     filename="healthcare-ai-q8_0-unsloth.Q8_0.gguf",
-    tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("moriire/healthcare-ai-q8_0/healthcare-ai-q8_0-unsloth.Q8_0.gguf"),
+    tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("moriire/healthcare-ai-q8_0"),
     verbose=False,
      n_ctx=256,
      n_gpu_layers=0,