simpletransformers
Questgen.ai
Our great sponsors
| simpletransformers | Questgen.ai | |
|---|---|---|
| 6 | 3 | |
| 3,984 | 872 | |
| - | - | |
| 7.3 | 6.3 | |
| about 1 month ago | 5 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.
simpletransformers
-
Huggingface is a great idea poorly executed.
You might try this: https://github.com/ThilinaRajapakse/simpletransformers
-
Gpt 2 124m using transformers
https://github.com/ThilinaRajapakse/simpletransformers/blob/master/simpletransformers/language_generation/language_generation_model.py#L146
-
Neural Search Tutorial
Getting embeddings from BERT Encoder
-
Neural Search Step-by-Step
Tutorial includes: - What is the Neural Search? - Getting embeddings from BERT Encoder - Using vector search engine Qdrant - Creating an API server with FastAPI.
-
Document Classification
If you want to do text classification hugging face transformers is great. There's also a simple version for it: https://github.com/ThilinaRajapakse/simpletransformers
-
A Shortly like user interface for GPT 2?
Here is an example script to finetune a GPT-2 model: https://github.com/ThilinaRajapakse/simpletransformers/blob/master/examples/language_generation/fine_tune.py
Questgen.ai
-
Yes/No style Question and Answer Generation
I have tried to do some searching for models but there don't seem to be ones that do what I am looking for. The closest I found was Questgen, but it only generated the questions and they, more often than, not did not make sense - especially for the types of questions I was looking to generate.
- [D] How to create a question answering system with a (potentially very large) corpus of text?
-
Creating a Wikipedia Question/Answer generator
This library might be of help https://github.com/ramsrigouthamg/Questgen.ai
What are some alternatives?
BERTweet - BERTweet: A pre-trained language model for English Tweets (EMNLP-2020)
fastT5 - ⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.
minGPT - A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
FARM - :house_with_garden: Fast & easy transfer learning for NLP. Harvesting language models for the industry. Focus on Question Answering.
layout-parser - A Unified Toolkit for Deep Learning Based Document Image Analysis
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.
kiri - Backprop makes it simple to use, finetune, and deploy state-of-the-art ML models.
fastapi - FastAPI framework, high performance, easy to learn, fast to code, ready for production
kiri - Kiri is a visual tool designed for reviewing schematics and layouts of KiCad projects that are version-controlled with Git.
rasa - 💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants
MLH-Quizzet - This is a smart Quiz Generator that generates a dynamic quiz from any uploaded text/PDF document using NLP. This can be used for self-analysis, question paper generation, and evaluation, thus reducing human effort.