allennlp
jiant
| allennlp | jiant | |
|---|---|---|
| 13 | 2 | |
| 11,337 | 1,608 | |
| - | 0.2% | |
| 8.4 | 0.0 | |
| over 1 year ago | 10 months ago | |
| Python | Python | |
| Apache License 2.0 | MIT License |
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.
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 π€¬
-
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)
jiant
-
Any recommendation for the replacement of the toolkit jiant? [Research] [Discussion]
I am doing research in NLP with the toolkit jiant (https://github.com/nyu-mll/jiant). It is a quite nice and easy-to-use tool. Unfortunately, it stopped being maintained. I wonder is there any other recommendation that I can use to replace it?
-
Looking for a code base to implement multi-task learning in NLP
Jiant should fulfill 1, 2, 4 and 5.
What are some alternatives?
cedille-ai - βοΈ Cedille is a large French language model (6B), released under an open-source license
kiri - Backprop makes it simple to use, finetune, and deploy state-of-the-art ML models.
fairseq - Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
SGDepth - [ECCV 2020] Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance
mesh-transformer-jax - Model parallel transformers in JAX and Haiku
bertviz - BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
lm-evaluation-harness - A framework for few-shot evaluation of language models.
haystack - :mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
python-sutime - Python wrapper for Stanford CoreNLP's SUTime
PaddleNLP - π Easy-to-use and powerful NLP and LLM library with π€ Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including πText Classification, π Neural Search, β Question Answering, βΉοΈ Information Extraction, π Document Intelligence, π Sentiment Analysis etc.
PaddleHub - Awesome pre-trained models toolkit based on PaddlePaddle. (400+ models including Image, Text, Audio, Video and Cross-Modal with Easy Inference & Serving)
YOLOP - You Only Look Once for Panopitic Driving Perception.οΌMIR2022οΌ