datablations
DB-GPT
datablations | DB-GPT | |
---|---|---|
6 | 10 | |
290 | 11,055 | |
3.8% | 5.0% | |
6.9 | 9.9 | |
about 1 month ago | 5 days ago | |
Jupyter Notebook | 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.
datablations
-
Gemini is only 1x Chinchilla, so it undertrained for production
1x chinchilla means it's not really undertrained but that more could be squeezed without excessive difficulty https://arxiv.org/abs/2305.16264
- Can LLMs learn from a single example?
-
Chinchilla’s Death
You might want to give a read to "Scaling Data-Constrained Language Models" [1]. They basically generalized the Chinchilla scaling law by investigating behavior on multi-epoch runs.
[1] https://arxiv.org/abs/2305.16264
-
RWKV Pile+ seems to be training on far more tokens than any LLM ever has
I would imagine that there is a lot of overlap, yeah. That said, training on repeated data does seem to be effective at this level.
-
(2/2) May 2023
Scaling Data-Constrained Language Models (https://arxiv.org/abs/2305.16264)
- How to Keep Scaling Large Language Models when Data Runs Out? A New AI Research Trains 400 Models with up to 9B Parameters and 900B Tokens to Create an Extension of Chinchilla Scaling Laws for Repeated Data
DB-GPT
-
(2/2) May 2023
Interact your data and environment using the local GPT (https://github.com/csunny/DB-GPT)
- FLaNK Stack Weekly 29 may 2023
- GitHub - csunny/DB-GPT: Interact your data and environment using the local GPT, no data leaks, 100% privately, 100% security
- DB-GPT - OSS to interact with your local LLM
- Show HN: DB-GPT, an LLM tool for database
What are some alternatives?
TinyLlama - The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
private-gpt - Interact with your documents using the power of GPT, 100% privately, no data leaks
airoboros - Customizable implementation of the self-instruct paper.
GPTCache - Semantic cache for LLMs. Fully integrated with LangChain and llama_index.
tree-of-thoughts - Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%
gorilla - Gorilla: An API store for LLMs
prompt-engineering - Tips and tricks for working with Large Language Models like OpenAI's GPT-4.
zamm - Experimental AI chat app
SuperAGI - <⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.
Propan - Propan is a powerful and easy-to-use Python framework for building event-driven applications that interact with any MQ Broker
chathub - All-in-one chatbot client
jj - JSON Stream Editor (command line utility)