-
Hi Yang Heng, I am trying to train the model from the checkpoint with custom data. I have already labelled the data in the correct format and also used convert_apc_set_to_atepc_set with no problem at …
-
When i try to fine tuning wizard-2 7b got the error: TypeError: MistralForCausalLM.forward() got an unexpected keyword argument 'causal_mask'.
Full stack info as follow:
model loading
==((====))=…
-
We have to do a fair amount of text preprocessing of our data before feeding it into tensorflow. Since the text manipulation abilities of tensorflow and tensorflow tranform are still relatively immatu…
-
I've got this bug report from someone on discord. He installs a language, and it shows success. Python does did throw an error. However he cannot switch to the language, and when refreshes the page, i…
-
#### Problem description
Hello, I'm new on gensim and I try to implement a (simple) W2V on my sentences. I cut out my sentences in batch of 10000 sentences, for each batch I apply the model with up…
-
## Description
After using new docker to make tests runnable on mxnet 1.8.0 in #1558 , I find there are some CPU tests will fail.
Some failed tests
test_models.py::test_big_rnn_model_share_params
…
-
As the title say, the dependency of Data-Juicer is heavy. I must install the total environment if I only want to use one OP.
TODO: Set installment for each OP, for example `pip install .[OP_NAME]`
-
## Overview
When building workflows, users spend most of their time writing simple to advanced jobs on OpenFn. We'd like to harness AI to write job expressions based on english text requirements
…
-
According to the [`spacy_install()` documentation](https://spacyr.quanteda.io/reference/spacy_install.html), one can provide a vector of multiple lang_models if you'd like multiple installed at once. …
-
I have followed the advice from various past issues asking to install the dev version of this package but still get this error:
```
AttributeError: 'JobNER' object has no attribute 'nlp'
```
I…