Langchain-Chatchat
Langchain-Chatchat copied to clipboard
chatchat-space
一直停在文本加载处
一直停在文本加载处
(chatglm) D:\langchain-ChatGLM-master>python cli_demo.py
Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a revision is encouraged when loading a configuration with custom code to ensure no malicious code has been contributed in a newer revision.
Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision.
Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████| 8/8 [00:05<00:00, 1.49it/s]
No sentence-transformers model found with name C:\Users\MSN/.cache\torch\sentence_transformers\GanymedeNil_text2vec-large-chinese. Creating a new one with MEAN pooling.
No sentence-transformers model found with name C:\Users\MSN/.cache\torch\sentence_transformers\GanymedeNil_text2vec-large-chinese. Creating a new one with MEAN pooling.
Input your local knowledge file path 请输入本地知识文件路径：D:\langchain-ChatGLM-master\content\state_of_the_search.txt
卡在最后一步一个多小时了，请问这正常吗？ python3.8，cuda11.7，环境与项目相同，怎么破
感觉不太正常，请问先存占用情况怎么样？
bookwoods @.***>于2023年4月15日 周六22:29写道：
一直停在文本加载处 (chatglm) D:\langchain-ChatGLM-master>python cli_demo.py Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision. Explicitly passing a revision is encouraged when loading a configuration with custom code to ensure no malicious code has been contributed in a newer revision. Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision. Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████| 8/8 [00:05<00:00, 1.49it/s] No sentence-transformers model found with name C:\Users\MSN/.cache\torch\sentence_transformers\GanymedeNil_text2vec-large-chinese. Creating a new one with MEAN pooling. No sentence-transformers model found with name C:\Users\MSN/.cache\torch\sentence_transformers\GanymedeNil_text2vec-large-chinese. Creating a new one with MEAN pooling. Input your local knowledge file path 请输入本地知识文件路径：D:\langchain-ChatGLM-master\content\state_of_the_search.txt
卡在最后一步一个多小时了，请问这正常吗？ python3.8，cuda11.7，环境与项目相同，怎么破
— Reply to this email directly, view it on GitHub https://github.com/imClumsyPanda/langchain-ChatGLM/issues/108, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABLH5EV7RDGZFC743SMP3OTXBKWFVANCNFSM6AAAAAAW7OMQXY . You are receiving this because you are subscribed to this thread.Message ID: @.***>
感觉不太正常，请问先存占用情况怎么样？ bookwoods @.>于2023年4月15日 周六22:29写道： … 一直停在文本加载处 (chatglm) D:\langchain-ChatGLM-master>python cli_demo.py Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision. Explicitly passing a revision is encouraged when loading a configuration with custom code to ensure no malicious code has been contributed in a newer revision. Explicitly passing a revision is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision. Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████| 8/8 [00:05<00:00, 1.49it/s] No sentence-transformers model found with name C:\Users\MSN/.cache\torch\sentence_transformers\GanymedeNil_text2vec-large-chinese. Creating a new one with MEAN pooling. No sentence-transformers model found with name C:\Users\MSN/.cache\torch\sentence_transformers\GanymedeNil_text2vec-large-chinese. Creating a new one with MEAN pooling. Input your local knowledge file path 请输入本地知识文件路径：D:\langchain-ChatGLM-master\content\state_of_the_search.txt 卡在最后一步一个多小时了，请问这正常吗？ python3.8，cuda11.7，环境与项目相同，怎么破 — Reply to this email directly, view it on GitHub <#108>, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABLH5EV7RDGZFC743SMP3OTXBKWFVANCNFSM6AAAAAAW7OMQXY . You are receiving this because you are subscribed to this thread.Message ID: @.>
显卡24G的4090显存占用12G
如果使用默认的6b+text2vec模型，建议使用显存至少15GB的显卡，详细请见 README.md 中硬件配置相关内容
12G可以考虑使用chatglm-6b-int4模型+text2vec
bookwoods @.***>于2023年4月17日 周一19:21写道：
还没有，放弃了，再试试其他办法
— Reply to this email directly, view it on GitHub https://github.com/imClumsyPanda/langchain-ChatGLM/issues/108#issuecomment-1511159993, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABLH5ET5ETW6LSRBCKM7ILTXBURT7ANCNFSM6AAAAAAW7OMQXY . You are receiving this because you commented.Message ID: @.***>