EasyEdit
ReAct
| EasyEdit | ReAct | |
|---|---|---|
| 6 | 1 | |
| 1,435 | 1,619 | |
| 9.9% | - | |
| 9.8 | 4.8 | |
| 5 days ago | 3 months ago | |
| Jupyter Notebook | Jupyter Notebook | |
| MIT License | 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.
EasyEdit
-
ChatGPT provides false information about people, and OpenAI can't correct it
> The article talks about OpenAI being unwilling to correct errors. But they just can’t.
There are actually several algorithms intended to allow fact editing in LLMs: https://github.com/zjunlp/EasyEdit?tab=readme-ov-file#curren...
They don't work perfectly (e.g. "Tim Cook is CEO of Apple" and "The CEO of Apple is Tim Cook" for some reason have to be edited separately) but there are certainly techniques available.
- Looking for Paper about LLM Fine Tuning for specific topic / Alignment Paper
- Is it possible to instill new facts and knowledge during the fine-tuning
- EasyEdit: An Easy-to-Use Knowledge Editing Framework for Large Language Models
-
Meta to release open-source commercial AI model
> It's not like Meta can remove these books from the training set without retraining from scratch (or at least the last checkpoint before they were used).
They probably can:
https://github.com/zjunlp/EasyEdit
> I wonder if this is going to cause issues down the road.
There are some popular Stable Diffusion models, being run in small businesses, that I am certain have CSAM in them because they have a particular 4chan model in their merging lineage.
... And yet, it hasn't blown up yet? I have no explanation, but running illegal weights seems more sustainable than I would expect.
- Funnily enough AI models must follow privacy law including right to be forgotten
ReAct
What are some alternatives?
AutoCog - Automaton & Cognition
ragas - Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines
llm-search - Querying local documents, powered by LLM
LLM-Training-Puzzles - What would you do with 1000 H100s...
awesome-refreshing-llms - EMNLP'23 survey: a curation of awesome papers and resources on refreshing large language models (LLMs) without expensive retraining.
Get-Things-Done-with-Prompt-Engineering-and-LangChain - LangChain & Prompt Engineering tutorials on Large Language Models (LLMs) such as ChatGPT with custom data. Jupyter notebooks on loading and indexing data, creating prompt templates, CSV agents, and using retrieval QA chains to query the custom data. Projects for using a private LLM (Llama 2) for chat with PDF files, tweets sentiment analysis.
memit - Mass-editing thousands of facts into a transformer memory (ICLR 2023)
FastLoRAChat - Instruct-tune LLaMA on consumer hardware with shareGPT data
mistral-src - Reference implementation of Mistral AI 7B v0.1 model.
hyde - HyDE: Precise Zero-Shot Dense Retrieval without Relevance Labels