hankcs
hankcs
Tried again, still Access Denied: - aws s3 ls s3://mt-qrecc/collection-paragraph/ - curl https://mt-qrecc.s3.amazonaws.com/collection-paragraph/
Hi @HarshTrivedi , thank you for your prompt reply. I asked this because I'm doing error analysis of these LLMs. The first step is to obtain API responses by feeding...
Thank you, will do!
Not sure what did you put in the docs, but it's supposed to be a str (can contain many sents then the tokenizer will split it into several sents).
Did you put a tokenizer in your tools? I just ran the POS and it works fine. ``` from elit.component import NERFlairTagger from elit.component.tokenizer import EnglishTokenizer from elit.structure import Document...
> > > Did you put a tokenizer in your tools? I just ran the POS and it works fine. > > > ``` > > > from elit.component import...
The embedding file in config.ini is referring to `/home/zyang68/data/trained_embeddings/dim100.vec.bak`. Now I changed it to `data/embedding/fasttext100.vec.txt`. Please use the new `config.ini` in `~/elit/data/model/dep/jumbo-fasttext100`.
Yes, I updated the first line `data/embedding/fasttext100.vec.txt` to `%(data_dir)s/data/embedding/fasttext100.vec.txt`. Now it should work.
Hi Gary, sorry for the delay, just survived final weeks. In this patch, we can override the embedding path: ```python parser.load(model_path, embedding_path) ```
You need mxnet gpu version.