kiri
qagnn
kiri | qagnn | |
---|---|---|
12 | 6 | |
240 | 588 | |
0.0% | - | |
3.2 | 0.0 | |
almost 3 years ago | about 1 year ago | |
Python | Python | |
GNU General Public License v3.0 or later | 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.
kiri
-
[P][D] NLP question - Question Answering AI
I'm one of the authors of Backprop, a library built for transfer learning.
-
Backprop: Use and finetune models in a single line of code
I'd like to share Backprop, an open source library I've been co-authoring for the last few months.
-
[P] Backprop Model Hub: a curated list of state-of-the-art models
We've also got an open-source library that makes using + finetuning these models possible in a few lines of code.
- Show HN: Backprop – a simple library to use and finetune state-of-the-art models
- Show HN: Backprop – a library to easily finetune and use state-of-the-art models
-
[P] Backprop: a library to easily finetune and use state-of-the-art models
I'd like to share Backprop, a Python library I've been co-authoring for the last few months. Our goal is to make finetuning and using models as easy as possible, even without extensive ML experience.
-
GPT Neo: open-source GPT-3-like model with pretrained weights available
You might get some really promising results with finetuning.
If anything, you could build writing assistance that almost automates responses.
I've been co-authoring a library that lets you finetune such models in a single line of code.
https://github.com/backprop-ai/backprop
In specific the text generation finetuning example should be what you are looking for: https://github.com/backprop-ai/backprop/blob/main/examples/F...
Hope this helps, happy to chat more about it. Pretty curious about the results.
-
NLP Model for extracting specific text from raw text
Here's an example Jupyter Notebook for finetuning T5. Full disclosure, I work on this library myself -- but it could be helpful.
-
[D] Need help with document classifier and later prediction of text
I'm working on a library that hopefully makes working with some of these a bit easier -- here's an example notebook for running text classification with the BART checkpoint, if you're interested. If you need more task-specific finetuning for text classification, that's going to be rolled out in the near future.
-
Generating notes from text
I'm working on a library that includes a few different ML tasks, including summarisation. It uses a pretrained version of Google's T5 transformer model, which we host on Hugging Face with some details on how it was trained.
qagnn
-
[D] what percent of top conference papers fudge results?
QA-GNN (https://github.com/michiyasunaga/qagnn from a Stanford lab) had some issues with their evaluation, but more importantly this work 'GNN is counting?...' (https://openreview.net/forum?id=hzmQ4wOnSb) showed that they can achieve better results with an extremely simplistic 1-dim GNN model - so the performance of QA-GNN was mainly due to data. AFAIK there were discussions around this, but now if you go to QA-GNN repo they have disabled issues tab.
- Stanford’s AI Researchers Introduce QA-GNN Model That Jointly Reasons With Language Models And Knowledge Graphs
- [R] Stanford’s AI Researchers Introduce QA-GNN Model That Jointly Reasons With Language Models And Knowledge Graphs
What are some alternatives?
gpt-neox - An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
RecBole - A unified, comprehensive and efficient recommendation library
simpletransformers - Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI
kiri - Kiri is a visual tool designed for reviewing schematics and layouts of KiCad projects that are version-controlled with Git.
CLIP - CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
LinkBERT - [ACL 2022] LinkBERT: A Knowledgeable Language Model 😎 Pretrained with Document Links
Questgen.ai - Question generation using state-of-the-art Natural Language Processing algorithms
prompt-lib - A set of utilities for running few-shot prompting experiments on large-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.
pal - PaL: Program-Aided Language Models (ICML 2023)
BERTweet - BERTweet: A pre-trained language model for English Tweets (EMNLP-2020)
question_extractor - Generate question/answer training pairs out of raw text.