Sameera Horawalavithana

**Describe the bug** Unable to run the evaluate.py with a gpt-neox model trained with pp=0, mp=1. **To Reproduce** Train a 13B model with zero stage 2, pp=0, mp=1. Save checkpoint....

**Is your feature request related to a problem? Please describe.** To load gpt-neox models using HF AutoModel.from_pretrained functionality. This will broaden the usage of gpt-neox models within the HF eco-system....

Handling multiple fields of the custom input data in the preprocess_data.py

6

**Describe the bug** preprocess_data script expects to have "text" column in the json input regardless of the json-keys passed in the arguments. This is due to lmd.Reader(fname).stream_data() expects to have...

FLAVA code

4

In the original FLAVA paper [1], it cited MMF for the implementation. We want to check whether we can access the FLAVA implementation in this codebase. [1] Singh, Amanpreet, et...

Hello, Has anybody used GRAN to generate the user interaction network structure on Twitter?

Does SpERT work with GPT models?

1

Hi, just wondering whether there are any efforts in the SpERT + GPT model integration?

Access to 2.5 million materials science articles

1

Hello, Is there any plan to release the article database for non-profit/academic research work?

Fix issue related to list conversion

1

Error: `File "../graphite/preprocessing.py", line 45, in pick_edges u, v = G_edges[i] File "../lib/python/site-packages/networkx/classes/reportviews.py", line 929, in __getitem__ u, v = e TypeError: 'int' object is not iterable` Fix by converting...

Visualize the rumor spread using Twitter data

3

Given the facts/ claim made in news-documents, this task to visualize how they spread in Twitter. As an example, if there are multiple facts/ claims regarding "Wilpattu Deforestation" in news-documents,...

This task is to introduce "key-word" search over the news document corpus collected in Elasticsearch. Following steps are required to complete the task: 1. Implement a wrapper on top of...