We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
问题描述 / Problem Description Qwen1.5-14B-Chat在Langchain-Chatchat启动,长时间停止在Loading checkpoint shards: 75%
操作系统:Linux-4.19.24-7.34.cbp.al7.x86_64-x86_64-with-glibc2.35. python版本:3.11.9 (main, Apr 19 2024, 16:48:06) [GCC 11.2.0] 项目版本:v0.2.10 langchain版本:0.0.354. fastchat版本:0.2.35
当前使用的分词器:ChineseRecursiveTextSplitter 当前启动的LLM模型:['Qwen1.5-14B-Chat'] @ cuda {'device': 'cuda', 'host': '0.0.0.0', 'infer_turbo': False, 'model_path': '/mnt/workspace/Qwen1.5-14B-Chat', 'model_path_exists': True, 'port': 20002} 当前Embbedings模型: bge-large-zh-v1.5 @ cuda ==============================Langchain-Chatchat Configuration==============================
2024-05-19 10:40:47,918 - startup.py[line:655] - INFO: 正在启动服务: 2024-05-19 10:40:47,919 - startup.py[line:656] - INFO: 如需查看 llm_api 日志,请前往 /mnt/workspace/Langchain-Chatchat/logs /opt/conda/envs/lc/lib/python3.11/site-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: 模型启动功能将于 Langchain-Chatchat 0.3.x重写,支持更多模式和加速启动,0.2.x中相关功能将废弃 warn_deprecated( 2024-05-19 10:40:53 | ERROR | stderr | INFO: Started server process [17244] 2024-05-19 10:40:53 | ERROR | stderr | INFO: Waiting for application startup. 2024-05-19 10:40:53 | ERROR | stderr | INFO: Application startup complete. 2024-05-19 10:40:53 | ERROR | stderr | INFO: Uvicorn running on http://0.0.0.0:20000 (Press CTRL+C to quit) 2024-05-19 10:40:54 | INFO | model_worker | Loading the model ['Qwen1.5-14B-Chat'] on worker 90de9bfd ... Loading checkpoint shards: 0%| | 0/8 [00:00<?, ?it/s] Loading checkpoint shards: 12%|████████████▋ | 1/8 [00:21<02:28, 21.18s/it] Loading checkpoint shards: 25%|█████████████████████████▎ | 2/8 [00:43<02:11, 21.84s/it] Loading checkpoint shards: 38%|█████████████████████████████████████▉ | 3/8 [01:05<01:49, 21.96s/it] Loading checkpoint shards: 50%|██████████████████████████████████████████████████▌ | 4/8 [01:27<01:27, 21.99s/it] Loading checkpoint shards: 62%|███████████████████████████████████████████████████████████████▏ | 5/8 [01:49<01:05, 22.00s/it] Loading checkpoint shards: 75%|███████████████████████████████████████████████████████████████████████████▊ | 6/8 [02:12<00:44, 22.18s/it]
The text was updated successfully, but these errors were encountered:
会不会是你的机器内存不足了,所以载入不完
Sorry, something went wrong.
资源充足,24G显卡,启动的时候都没怎么用显存。
内存,哥~
感谢兄弟,其实也不是内存,是Qwen1.5-14B-Chat需要24G以上的显存。
No branches or pull requests
问题描述 / Problem Description
Qwen1.5-14B-Chat在Langchain-Chatchat启动,长时间停止在Loading checkpoint shards: 75%
操作系统:Linux-4.19.24-7.34.cbp.al7.x86_64-x86_64-with-glibc2.35.
python版本:3.11.9 (main, Apr 19 2024, 16:48:06) [GCC 11.2.0]
项目版本:v0.2.10
langchain版本:0.0.354. fastchat版本:0.2.35
当前使用的分词器:ChineseRecursiveTextSplitter
当前启动的LLM模型:['Qwen1.5-14B-Chat'] @ cuda
{'device': 'cuda',
'host': '0.0.0.0',
'infer_turbo': False,
'model_path': '/mnt/workspace/Qwen1.5-14B-Chat',
'model_path_exists': True,
'port': 20002}
当前Embbedings模型: bge-large-zh-v1.5 @ cuda
==============================Langchain-Chatchat Configuration==============================
2024-05-19 10:40:47,918 - startup.py[line:655] - INFO: 正在启动服务:
2024-05-19 10:40:47,919 - startup.py[line:656] - INFO: 如需查看 llm_api 日志,请前往 /mnt/workspace/Langchain-Chatchat/logs
/opt/conda/envs/lc/lib/python3.11/site-packages/langchain_core/_api/deprecation.py:117: LangChainDeprecationWarning: 模型启动功能将于 Langchain-Chatchat 0.3.x重写,支持更多模式和加速启动,0.2.x中相关功能将废弃
warn_deprecated(
2024-05-19 10:40:53 | ERROR | stderr | INFO: Started server process [17244]
2024-05-19 10:40:53 | ERROR | stderr | INFO: Waiting for application startup.
2024-05-19 10:40:53 | ERROR | stderr | INFO: Application startup complete.
2024-05-19 10:40:53 | ERROR | stderr | INFO: Uvicorn running on http://0.0.0.0:20000 (Press CTRL+C to quit)
2024-05-19 10:40:54 | INFO | model_worker | Loading the model ['Qwen1.5-14B-Chat'] on worker 90de9bfd ...
Loading checkpoint shards: 0%| | 0/8 [00:00<?, ?it/s]
Loading checkpoint shards: 12%|████████████▋ | 1/8 [00:21<02:28, 21.18s/it]
Loading checkpoint shards: 25%|█████████████████████████▎ | 2/8 [00:43<02:11, 21.84s/it]
Loading checkpoint shards: 38%|█████████████████████████████████████▉ | 3/8 [01:05<01:49, 21.96s/it]
Loading checkpoint shards: 50%|██████████████████████████████████████████████████▌ | 4/8 [01:27<01:27, 21.99s/it]
Loading checkpoint shards: 62%|███████████████████████████████████████████████████████████████▏ | 5/8 [01:49<01:05, 22.00s/it]
Loading checkpoint shards: 75%|███████████████████████████████████████████████████████████████████████████▊ | 6/8 [02:12<00:44, 22.18s/it]
The text was updated successfully, but these errors were encountered: