[BUG/Help] <ptuning成功后，运行web_demo.py，输入promts后后台抛异常>

[StarRanger]

Is there an existing issue for this?

• I have searched the existing issues

Current Behavior

ptuning成功后，运行web_demo.py，输入promts后后台抛异常。

Expected Behavior

No response

Steps To Reproduce

1. 运行ptuning文件夹下的bash trains.sh成功，数据集是自己准备的中文数据集。
2. 将web_demo.py下面的ChatGLM-6B,替换称为ptuning下面最新的checkpoint路径，启动也成功。
3. 在输入框输入原本数据集中就存在的prompts后，后端服务日志抛异常如下：
   This share link expires in 72 hours. For free permanent hosting and GPU upgrades (NEW!), check out Spaces: https://huggingface.co/spaces
   Traceback (most recent call last):
   File "/root/.conda/envs/python39/lib/python3.9/site-packages/gradio/routes.py", line 393, in run_predict
   output = await app.get_blocks().process_api(
   File "/root/.conda/envs/python39/lib/python3.9/site-packages/gradio/blocks.py", line 1108, in process_api
   result = await self.call_function(
   File "/root/.conda/envs/python39/lib/python3.9/site-packages/gradio/blocks.py", line 929, in call_function
   prediction = await anyio.to_thread.run_sync(
   File "/root/.conda/envs/python39/lib/python3.9/site-packages/anyio/to_thread.py", line 31, in run_sync
   return await get_asynclib().run_sync_in_worker_thread(
   File "/root/.conda/envs/python39/lib/python3.9/site-packages/anyio/_backends/_asyncio.py", line 937, in run_sync_in_worker_thread
   return await future
   File "/root/.conda/envs/python39/lib/python3.9/site-packages/anyio/_backends/_asyncio.py", line 867, in run
   result = context.run(func, *args)
   File "/root/.conda/envs/python39/lib/python3.9/site-packages/gradio/utils.py", line 490, in async_iteration
   return next(iterator)
   File "/root/llm/ChatGLM-6B-main/web_demo.py", line 63, in predict
   for response, history in model.stream_chat(tokenizer, input, history, max_length=max_length, top_p=top_p,
   File "/root/.conda/envs/python39/lib/python3.9/site-packages/torch/utils/_contextlib.py", line 35, in generator_context
   response = gen.send(None)
   File "/root/.cache/huggingface/modules/transformers_modules/checkpoint-3000/modeling_chatglm.py", line 1281, in stream_chat
   for outputs in self.stream_generate(**inputs, **gen_kwargs):
   File "/root/.conda/envs/python39/lib/python3.9/site-packages/torch/utils/_contextlib.py", line 35, in generator_context
   response = gen.send(None)
   File "/root/.cache/huggingface/modules/transformers_modules/checkpoint-3000/modeling_chatglm.py", line 1356, in stream_generate
   model_inputs = self.prepare_inputs_for_generation(input_ids, **model_kwargs)
   File "/root/.cache/huggingface/modules/transformers_modules/checkpoint-3000/modeling_chatglm.py", line 1091, in prepare_inputs_for_generation
   mask_positions = [seq.index(mask_token) for seq in seqs]
   File "/root/.cache/huggingface/modules/transformers_modules/checkpoint-3000/modeling_chatglm.py", line 1091, in
   mask_positions = [seq.index(mask_token) for seq in seqs]
   ValueError: 130000 is not in list

这是否还需要加载原本chatglm-6b的那几个.bin文件啊？

Environment

- OS:Centos 7.6
- Python:3.9
- Transformers:4.28.0
- PyTorch:2.0.0+cu117
- CUDA Support (`python -c "import torch; print(torch.cuda.is_available())"`) : True

Anything else?

No response

[duzx16]

Duplicate of #457