MOSS
MOSS copied to clipboard
OpenMOSS
An open-source tool-augmented conversational language model from Fudan University
在centos上部署好，运行moss_gui_demo.py，已经提示Running on local URL: http://127.0.0.1:7860，但是网页打开，显示无法访问
运行报错
UserWarning: where received a uint8 condition tensor. This behavior is deprecated and will be removed in a future version of PyTorch. Use a boolean condition instead. (Triggered internally at ../aten/src/ATen/native/TensorCompare.cpp:402.)...
D:\AI\MOSS>python moss_cli_demo.py Traceback (most recent call last): File "D:\AI\MOSS\moss_cli_demo.py", line 3, in import torch ModuleNotFoundError: No module named 'torch' D:\AI\MOSS>pip install torch Requirement already satisfied: torch in d:\anaconda3\lib\site-packages (1.10.1) Requirement...
Traceback (most recent call last): File "/mnt/e/code/code_xuexi/github/MOSS-main/moss_cli_demo.py", line 33, in model = load_checkpoint_and_dispatch( File "/root/anaconda3/envs/moss/lib/python3.8/site-packages/accelerate/big_modeling.py", line 479, in load_checkpoint_and_dispatch load_checkpoint_in_model( File "/root/anaconda3/envs/moss/lib/python3.8/site-packages/accelerate/utils/modeling.py", line 924, in load_checkpoint_in_model checkpoint = load_state_dict(checkpoint_file, device_map=device_map)...
https://github.com/lvwzhen/law-cn-ai https://github.com/suno-ai/bark https://github.com/mlc-ai/web-llm https://xenova.github.io/transformers.js
使用的模型是003的plugin int4模型，显卡是3090，报错时显存显示占用了12.5G。 具体报错信息如下： /opt/conda/conda-bld/pytorch_1670525552843/work/aten/src/ATen/native/cuda/IndexKernel.cu:92: operator(): block: [272,0,0], thread: [127,0,0] Assertion `index >= -sizes[i] && index < sizes[i] && "index out of bounds"` failed. Exception in thread Thread-7 (generate): Traceback (most...
我正在尝试在iMac上的VMwear Fusion的Linux Ubuntu虚拟机运行推理出现问题“RuntimeError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU and installed a driver from http://www.nvidia.com/Download/index.aspx” 我的电脑是inter CPU，AMD Radeon Pro 555X GPU，不支持CUDA...
