Update app.py

app.py

@@ -1,38 +1,45 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-from transformers import AutoModelForCausalLM, AutoTokenizer
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
 
 pretrained_model = "ykallan/SkuInfo-Qwen2.5-3B-Instruct"
-model = AutoModelForCausalLM.from_pretrained(pretrained_model)
-tokenizer = AutoTokenizer.from_pretrained(pretrained_model)
 
+client = InferenceClient(pretrained_model)
 
 def respond(
     message,
+    history: list[tuple[str, str]],
+    system_message,
     max_tokens,
     temperature,
     top_p,
 ):
-    messages = [{"role": "system", "content": "在以下商品名称中抽取出品牌、型号、主商品，并以JSON格式返回。"}]
+    messages = [{"role": "system", "content": system_message}]
+
+    for val in history:
+        if val[0]:
+            messages.append({"role": "user", "content": val[0]})
+        if val[1]:
+            messages.append({"role": "assistant", "content": val[1]})
 
     messages.append({"role": "user", "content": message})
-    input_ids = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-    model_inputs = tokenizer([input_ids], return_tensors="pt", padding=True)
-    
-    generate_config = {
-        "max_new_tokens": 128
-    }
-
-    generated_ids = model.generate(model_inputs.input_ids, **generate_config)
-    generated_ids = [
-        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
-    ]
-    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
-    return response
+
+    response = ""
+
+    for message in client.chat_completion(
+        messages,
+        max_tokens=max_tokens,
+        stream=True,
+        temperature=temperature,
+        top_p=top_p,
+    ):
+        token = message.choices[0].delta.content
+
+        response += token
+        yield response
 
 
 """