模型加载问题
#1
by
murphy
- opened
每次compute_score都会进行模型加载，耗时严重
0%| | 0/8 [00:00<?, ?it/s]You're using a LlamaTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
You're using a LlamaTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
You're using a LlamaTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
You're using a LlamaTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
You're using a LlamaTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
You're using a LlamaTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
You're using a LlamaTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
You're using a LlamaTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.
100%|██████████| 8/8 [00:12<00:00, 1.53s/it]
收到反馈。这个是会加载dataloader，而不是加载模型。
后续我们会尝试优化。
现在代码已经更新，在compute_score的时候可以传参use_dataloader=False来解决这个问题
现在代码已经更新，在compute_score的时候可以传参use_dataloader=False来解决这个问题
想问下这个代码更新到哪里了，我填了后报错了。
可以按这样的方式进行更新，git clone https://github.com/FlagOpen/FlagEmbedding.git+pip install .
可以按这样的方式进行更新，
git clone https://github.com/FlagOpen/FlagEmbedding.git+pip install .
我是用 xinference 部署也是遇到这个问题，耗时特别严重，也能用这个办法解决吗？
可以按这样的方式进行更新，
git clone https://github.com/FlagOpen/FlagEmbedding.git+pip install .我是用 xinference 部署也是遇到这个问题，耗时特别严重，也能用这个办法解决吗？
可以使用git clone https://github.com/FlagOpen/FlagEmbedding.git+pip install .更新代码，这样就可以在compute_score的时候设置参数use_dataloader=False，从而避免使用dataloader导致的额外耗时问题