inltk
allennlp
Our great sponsors
inltk | allennlp | |
---|---|---|
1 | 13 | |
811 | 11,337 | |
- | - | |
0.0 | 8.4 | |
3 months ago | over 1 year ago | |
Python | Python | |
MIT License | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
inltk
-
Which are top APIs for Indian languages mainly VR, OCR, Speech - Text - Speech?
The best tool will vary a little bit from language to language, but your best bets are probably the Indic NLP Library and iNLTK
allennlp
-
How to solve ConfigurationError using HuggingFace Token Classifier
No clue. So what I did was google the error. Here's what I found: https://github.com/allenai/allennlp/issues/4319
- AllenNLP will be unmaintained in December
- AllenNLP Is EOL
- Any recommendation for the replacement of the toolkit jiant? [Research] [Discussion]
- Cedille, the largest French language model, open source with a freely accessible playground
-
[P] Cedille, the largest French language model (6b), released in open source
Another aspect we had fun with is dataset filtering. We have run the whole C4 French dataset through the Detoxify classifier to clean it up 🤬
-
Any allennlp users in this sub?
https://github.com/allenai/allennlp/discussions looks active
- Multilingual C4 (mC4) Dataset now released
- C4 dataset released (800GB Common Crawl-derived text; T5 training data)
What are some alternatives?
DiffCSE - Code for the NAACL 2022 long paper "DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings"
cedille-ai - ✒️ Cedille is a large French language model (6B), released under an open-source license
SimCSE - [EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
fairseq - Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
smaller-labse - Applying "Load What You Need: Smaller Versions of Multilingual BERT" to LaBSE
mesh-transformer-jax - Model parallel transformers in JAX and Haiku
clip-as-service - 🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP
lm-evaluation-harness - A framework for few-shot evaluation of language models.
KitanaQA - KitanaQA: Adversarial training and data augmentation for neural question-answering models
python-sutime - Python wrapper for Stanford CoreNLP's SUTime
ModelNet40-C - Repo for "Benchmarking Robustness of 3D Point Cloud Recognition against Common Corruptions" https://arxiv.org/abs/2201.12296
PaddleHub - Awesome pre-trained models toolkit based on PaddlePaddle. (400+ models including Image, Text, Audio, Video and Cross-Modal with Easy Inference & Serving)