LinkBERT
qagnn
| LinkBERT | qagnn | |
|---|---|---|
| 2 | 6 | |
| 389 | 588 | |
| - | - | |
| 1.8 | 0.0 | |
| about 2 years ago | about 1 year 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.
LinkBERT
-
[D] Fine tuning LLM - VM requirements.
I am quite new to this - at the stage of experimenting. I would like to fine tune some large language model like LinkBert for instance: https://github.com/michiyasunaga/LinkBERT
-
Stanford AI Researchers Propose ‘LinkBERT’: A New Pretraining Method That Improves Language Model Training with Document Links
Continue reading | Check out the paper, github and blog post
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?
PaddleNLP - 👑 Easy-to-use and powerful NLP and LLM library with 🤗 Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including 🗂Text Classification, 🔍 Neural Search, ❓ Question Answering, ℹ️ Information Extraction, 📄 Document Intelligence, 💌 Sentiment Analysis etc.
kiri - Backprop makes it simple to use, finetune, and deploy state-of-the-art ML models.
CogVLM - a state-of-the-art-level open visual language model | 多模态预训练模型
RecBole - A unified, comprehensive and efficient recommendation library
transformers - 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
kiri - Kiri is a visual tool designed for reviewing schematics and layouts of KiCad projects that are version-controlled with Git.
uform - Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️
prompt-lib - A set of utilities for running few-shot prompting experiments on large-language models
LMFlow - An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
pal - PaL: Program-Aided Language Models (ICML 2023)
question_extractor - Generate question/answer training pairs out of raw text.