lora微调后没有pytorch_model.bin

[zhengshi119]

System Info / 系統信息

应该不是环境的问题

Who can help? / 谁可以帮助到您？

lora微调后没有pytorch_model.bin，运行comosite_demo的main.py会出错： Traceback (most recent call last): File "/usr/local/python3.10/lib/python3.10/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 584, in _run_script exec(code, module.dict) File "/root/workspace_zs/ChatGLM3-main/composite_demo/main.py", line 11, in import demo_chat, demo_ci, demo_tool File "/root/workspace_zs/ChatGLM3-main/composite_demo/demo_chat.py", line 7, in client = get_client() File "/usr/local/python3.10/lib/python3.10/site-packages/streamlit/runtime/caching/cache_utils.py", line 168, in wrapper return cached_func(*args, *kwargs) File "/usr/local/python3.10/lib/python3.10/site-packages/streamlit/runtime/caching/cache_utils.py", line 197, in call return self._get_or_create_cached_value(args, kwargs) File "/usr/local/python3.10/lib/python3.10/site-packages/streamlit/runtime/caching/cache_utils.py", line 224, in _get_or_create_cached_value return self._handle_cache_miss(cache, value_key, func_args, func_kwargs) File "/usr/local/python3.10/lib/python3.10/site-packages/streamlit/runtime/caching/cache_utils.py", line 280, in _handle_cache_miss computed_value = self._info.func(func_args, **func_kwargs) File "/root/workspace_zs/ChatGLM3-main/composite_demo/client.py", line 30, in get_client client = HFClient(MODEL_PATH, TOKENIZER_PATH, PT_PATH) File "/root/workspace_zs/ChatGLM3-main/composite_demo/client.py", line 147, in init prefix_state_dict = torch.load(os.path.join(pt_checkpoint, "pytorch_model.bin")) File "/usr/local/python3.10/lib/python3.10/site-packages/torch/serialization.py", line 699, in load with _open_file_like(f, 'rb') as opened_file: File "/usr/local/python3.10/lib/python3.10/site-packages/torch/serialization.py", line 230, in _open_file_like return _open_file(name_or_buffer, mode) File "/usr/local/python3.10/lib/python3.10/site-packages/torch/serialization.py", line 211, in init super(_open_file, self).init(open(name, mode)) FileNotFoundError: [Errno 2] No such file or directory: '/root/workspace/ChatGLM3-main/finetune_demo/output/checkpoint-3000/pytorch_model.bin'

Information / 问题信息

• [ ] The official example scripts / 官方的示例脚本
• [X] My own modified scripts / 我自己修改的脚本和任务

Reproduction / 复现过程

我将composite_demo中的client.py中的： MODEL_PATH = os.environ.get('MODEL_PATH', '/root/workspace/chatglm3-6b') PT_PATH = os.environ.get('PT_PATH', None) PRE_SEQ_LEN = int(os.environ.get("PRE_SEQ_LEN", 128)) TOKENIZER_PATH = os.environ.get("TOKENIZER_PATH", MODEL_PATH) 修改成了： MODEL_PATH = os.environ.get('MODEL_PATH', '/root/workspace/chatglm3-6b') PT_PATH = os.environ.get('PT_PATH', '/root/workspace_zs/ChatGLM3-main/finetune_demo/output_med_train30_dev16_pu/checkpoint-3000') PRE_SEQ_LEN = int(os.environ.get("PRE_SEQ_LEN", 128)) TOKENIZER_PATH = os.environ.get("TOKENIZER_PATH", MODEL_PATH)

注：我主要加上了PT_PATH = os.environ.get('PT_PATH', '/root/workspace_zs/ChatGLM3-main/finetune_demo/output_med_train30_dev16_pu/checkpoint-3000')

Expected behavior / 期待表现

希望可以使用微调后的模型，运行composite_demo。

[zRzRzRzRzRzRzR]

lora微调不是这么用的，查看我们的模型加载代码

[wangdae]

我用ptuning第一次微调还能生成model，后面再微调就一直生成不了