Update app.py

app.py

@@ -1,42 +1,29 @@
-import clueai
-
-# initialize the Clueai Client with an API Key
-cl = cl = clueai.Client('ffILfMwQydmK1YXyFplYc100010000010')
-
-# generate a prediction for a prompt
-
-generate_config = {
-    "do_sample": True,
-    "top_p": 0.8,
-    "max_length": 128,
-    "min_length": 10,
-    "length_penalty": 1.0,
-    "num_beams": 1
-  }
-# 如果需要自由调整参数自由采样生成，添加额外参数信息设置方式：generate_config=generate_config
-
-# 需要返回得分的话，指定return_likelihoods="GENERATION"
-
-import gradio as gr
-def question_answer(context, question):
-    pass  # Implement your question-answering model here...
-import gradio as gr
-
-def greet(question):
-    prompt = "" \
-    "问答：" \
-    "问题：" + question
-    "答案："
-    prediction = cl.generate(
-        model_name='clueai-base',
-        prompt=prompt)
-
-    return "小矢机器人：" + prediction.generations[0].text + "!"
-
-with gr.Blocks() as demo:
-    question = gr.Textbox(label="Question")
-    output = gr.Textbox(label="Answer Box")
-    greet_btn = gr.Button("Ask")
-    greet_btn.click(fn=greet, inputs=question, outputs=output)
-
-demo.launch()
+# 加载模型
+from transformers import T5Tokenizer, T5ForConditionalGeneration
+tokenizer = T5Tokenizer.from_pretrained("ClueAI/ChatYuan-large-v1")
+model = T5ForConditionalGeneration.from_pretrained("ClueAI/ChatYuan-large-v1")
+# 使用
+import torch
+from transformers import AutoTokenizer
+# 修改colab笔记本设置为gpu，推理更快
+device = torch.device('cuda')
+model.to(device)
+def preprocess(text):
+  text = text.replace("\n", "\\n").replace("\t", "\\t")
+  return text
+
+def postprocess(text):
+  return text.replace("\\n", "\n").replace("\\t", "\t")
+
+def answer(text, sample=True, top_p=1, temperature=0.7):
+  '''sample：是否抽样。生成任务，可以设置为True;
+  top_p：0-1之间，生成的内容越多样'''
+  text = preprocess(text)
+  encoding = tokenizer(text=[text], truncation=True, padding=True, max_length=768, return_tensors="pt").to(device) 
+  if not sample:
+    out = model.generate(**encoding, return_dict_in_generate=True, output_scores=False, max_new_tokens=512, num_beams=1, length_penalty=0.6)
+  else:
+    out = model.generate(**encoding, return_dict_in_generate=True, output_scores=False, max_new_tokens=512, do_sample=True, top_p=top_p, temperature=temperature, no_repeat_ngram_size=3)
+  out_text = tokenizer.batch_decode(out["sequences"], skip_special_tokens=True)
+  return postprocess(out_text[0])
+print("end...")