HyperOS

> 我今天也是卡这了，花了几个钟头，服了 确实是这样的，我用4.39.0以下的包可以正常运行了！ 但这个NOUGAT翻译的结果和“精准翻译PDF论文”有啥区别。

同样的问题： [Local Message] 插件调用出错: Traceback (most recent call last): File "d:\Program Files\whr\Python_Project\gpt_academic-master\toolbox.py", line 207, in decorated yield from f(main_input, llm_kwargs, plugin_kwargs, chatbot_with_cookie, history, *args, **kwargs) File "d:\Program Files\whr\Python_Project\gpt_academic-master\crazy_functions\批量翻译PDF文档_NOUGAT.py", line 93,...

def nougat_with_timeout(self, command, cwd, timeout=1e100): import subprocess from toolbox import ProxyNetworkActivate logging.info(f'正在执行命令 {command}') with ProxyNetworkActivate("Nougat_Download"): process = subprocess.Popen(command, shell=False, cwd=cwd, env=os.environ) try: stdout, stderr = process.communicate(timeout=timeout) except subprocess.TimeoutExpired: process.kill() stdout,...

请问您是怎么成功部署QWEN2.5模型的？我通过UI界面启动，如何使用都会出现CUDA OUT OF MEMORY，即便是`QWEN2.5-0.5B-INSTRUCT`我在一台3090电脑上使用。我通过shell启动，会直接出线requests.exceptions.JSONDecodeError: Expecting value: line 1 column 1 (char 0)

``` WARNING:root:No GPU found. Conversion on CPU is very slow. C:\Users\23243\anaconda3\envs\academic\Lib\site-packages\torch\functional.py:512: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3588.)...

Now the neural network is running and looks great! Can I save the best model parameters? I passed the path to the early stopping module, but the saved one doesn't...