Update app/llm.py

app/llm.py

@@ -22,7 +22,7 @@ class GenModel(BaseModel):
 
 class ChatModel(BaseModel):
     question: list
-    system: str = "You are a helpful AI assistant. You are chatting with a {0}. Help as much as you can."
+    system: str = "You are a helpful AI assistant. You are chatting with a human. Help as much as you can."
     #Also continuously ask for possible symptoms in order to atat a conclusive ailment or sickness and possible solutions.Remember, response in English."
     temperature: float = 0.8
     seed: int = 101
@@ -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("Qwen/Qwen1.5-0.5B"),
+    tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("moriire/healthcare-GGUF")
     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("Qwen/Qwen1.5-0.5B"),
+    tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained("moriire/healthcare-GGUF")
     verbose=False,
      n_ctx=4096,
      n_gpu_layers=0,