Update app.py

app.py

@@ -1,17 +1,24 @@
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForCausalLM
-import torch
+from ctransformers import AutoModelForCausalLM
 
 model_id = "Datangtang/GGUF_New_1B"
 
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id, device_map="cpu")
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    model_file="your_model.gguf",   # 改成你的 gguf 文件名
+    model_type="llama",
+    gpu_layers=0
+)
 
 def chat_fn(message):
-    inputs = tokenizer(message, return_tensors="pt")
-    outputs = model.generate(**inputs, max_new_tokens=150)
-    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+    response = model(message, max_new_tokens=200)
+    return response
 
-demo = gr.Interface(fn=chat_fn, inputs="text", outputs="text", title="My Finetuned LLM Chat")
+demo = gr.Interface(
+    fn=chat_fn,
+    inputs="text",
+    outputs="text",
+    title="My GGUF Model"
+)
 
 demo.launch()