FARM
tldr-transformers
| FARM | tldr-transformers | |
|---|---|---|
| 3 | 4 | |
| 1,723 | 167 | |
| 0.3% | - | |
| 0.0 | 0.0 | |
| 4 months ago | over 1 year ago | |
| 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.
FARM
-
Can someone please explain to me the differences between train, dev and test datasets?
I'm also trying to solve this task in a python notebook (.ipynb) using the FARM framework https://farm.deepset.ai/ and BERT model of huggingface https://huggingface.co/bert-base-uncased
-
Fine-Tuning Transformers for NLP
For anyone looking to fine-train transformers with less work, there is the FARM project (https://github.com/deepset-ai/FARM) which has some more or less ready-to-go configurations (classification, question answering, NER, and a couple of others). It's really almost "plug in a csv and run".
By the way, a pet peeve is sentiment detection. It's a useful method, but please be aware that it does not measure "sentiment" in a way that one would normally think, and that what it measure varies strongly across methods (https://www.tandfonline.com/doi/abs/10.1080/19312458.2020.18...).
-
Has anyone deployed a BERT like model across multiple tasks (Multi-class, NER, outlier detection)? Seeking advice.
You can use https://github.com/deepset-ai/FARM or https://github.com/nyu-mll/jiant for multitask learning. The second is more general.
tldr-transformers
- Show HN: The “tl;dr” of Recent Transformer Papers
-
Show HN: Tl;Dr” on Transformers Papers
With the explosion in research on all things transformers, it seemed there was a need to have a single table to distill the "tl;dr" of each paper's contributions relative to each other. Here is what I got so far: https://github.com/will-thompson-k/tldr-transformers . Would love feedback - and feel free to contribute too :)
-
[P] NLP "tl;dr" Notes on Transformers
In any case, I'm liking the first glance so far. I'd just transpose the summary tables so they wouldn't get so tightly squeezed: https://github.com/will-thompson-k/tldr-transformers/blob/main/notes/bart.md
With the explosion in work on all things transformers, I felt the need to keep a single table of the "tl;dr" of various papers to distill their main takeaways: https://github.com/will-thompson-k/tldr-transformers . Would love feedback!
What are some alternatives?
Giveme5W1H - Extraction of the journalistic five W and one H questions (5W1H) from news articles: who did what, when, where, why, and how?
NLP-progress - Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.
bertviz - BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
lemmatization-lists - Machine-readable lists of lemma-token pairs in 23 languages.
Questgen.ai - Question generation using state-of-the-art Natural Language Processing algorithms
azure-sql-db-openai - Samples on how to use Azure SQL database with Azure OpenAI
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.
long-range-arena - Long Range Arena for Benchmarking Efficient Transformers
happy-transformer - Happy Transformer makes it easy to fine-tune and perform inference with NLP Transformer models.
transformers-convert
BERT-NER - Pytorch-Named-Entity-Recognition-with-BERT
language-planner - Official Code for "Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents"