Update model.py

model.py

@@ -1,17 +1,10 @@
 
 from typing import Iterator
 
+from ctransformers import AutoModelForCausalLM
 
-
-model_id = 'xuqinyang/baichuan-13b-chat-ggml-int4'
-
-from huggingface_hub import snapshot_download,hf_hub_download
-#旧
-#snapshot_download(model_id, local_dir="./",revision="7f71a8abefa7b2eede3f74ce0564abe5fbe6874a")
-snapshot_download(model_id, local_dir="./",revision="b2414a0ceee68fe09c99ace44446cfc9a1c52b08")
-hf_hub_download(repo_id="baichuan-inc/Baichuan-13B-Chat",local_dir="./", filename="tokenizer.model")
-from llama_cpp import Llama
-llm = Llama(model_path="./ggml-model-q4_0.bin", n_ctx=4096,seed=-1)
+# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
+llm = AutoModelForCausalLM.from_pretrained("OpenBuddy/openbuddy-gguf", model_file="openbuddy-mistral-7b-v13.1-Q3_K.gguf", model_type="mistral", gpu_layers=0)
 
 def run(message: str,
         chat_history: list[tuple[str, str]],