mage
llm-foundry
mage | llm-foundry | |
---|---|---|
117 | 37 | |
1,771 | 3,718 | |
1.5% | 3.7% | |
10.0 | 9.7 | |
1 day ago | 3 days ago | |
Java | Python | |
MIT License | Apache License 2.0 |
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.
mage
- Open source rules engine for Magic: The Gathering
-
Fine Tuning Mistral 7B on Magic the Gathering Draft
Yeah, that surprised me too, given that https://github.com/magefree/mage is open source and pretty actively developed.
-
I Hacked Magic the Gathering: Arena for a 100% Win Rate
The project you want is http://xmage.today/
All cards available, and full rules engine.
-
Find Legal Moves in Brass Birmingham with Datalog
My guess is that fully modeling MtG's rules in Datalog would take a lot more work, because MtG's rules are a lot more complex. Looking through the source for one of the freely-available game engines like https://github.com/magefree/mage would probably be more informative, though.
-
Draft Time Spiral, Lorwyn, and other older sets online for free with the XMage Draft Historical Society!
There's a draft every day, with events at different starting times to accommodate players from around the world, plus asynchronous side events including Rich Draft, Team Sealed, and Rotisserie Draft. We play on XMage which has full rules enforcement like MTGO but is 100% free software.
-
Drafting Help
If you can tolerate some of its shortcomings, you can draft against bots on Xmage.
-
Bugged cards (xmage beta 1.4.51)
https://github.com/magefree/mage/issues is a more reliable place to report - this might not be a trivial fix
-
Xmage beta server update
Update: My problem happened because the launcher had reverted to the non-beta xmage home address on its own. You probably have the same problem. You need to go to settings, set branch to custom, and the xmage home address to http://xmage.today/
-
Seriously. Just woke up one morning and it made so much sense.
Real life example: The open source implementation of MTG card game multiplayer
- Firkraag not working
llm-foundry
-
Fine Tuning Mistral 7B on Magic the Gathering Draft
Related comment from gwern: https://news.ycombinator.com/item?id=38438859
Also - why qlora rather than a full finetune? Using LambdaLabs, It'd cost roughly the same as your quote. Cheaper I think if you're willing to gamble with fp8: https://github.com/mosaicml/llm-foundry/tree/main/scripts/tr.... And fewer hyperparameters to tune as well
-
Consortium launched to build the largest open LLM
Traditionally, training runs can "explode" and fail, but there are methods to incrementally back them up and resume when that happens, see https://www.mosaicml.com/blog/mpt-7b
-
Applying All Recent Innovations To Train a Code Model
MosaicML released the MPT-7B model, which has a context of 60k tokens, thanks to the ALiBi position encoding.
-
Fine Tuning Language Models
Most AI runners just ignore licensing and run LLaMA finetunes.
But if you want to avoid the non commercial LLaMA license, you have 3 good options for a base model.
- OpenLlama 13B
- MPT 30B
- Falcon 40B
Of these, Falcon 40B is very difficult to run (slow in 4 bit, basically requires a professional GPU, no good cpu offloading yet).
OpenLLaMA 13B only supports a context size of 2048 as of today... But that could change soon.
So you probably want MPT instruct 30B, specifically this one:
https://huggingface.co/TheBloke/mpt-30B-instruct-GGML
As the page says, you can try it out on a decent PC of your own with the OpenCL build of KoboldCPP. Change it to "instruct" mode, use the template on the page, offload as many layers as you can to your PC's dGPU, and run it in instruct mode. It may already work for your summarization needs.
If not, you can finetune it with MPT's code and summarization d
https://github.com/mosaicml/llm-foundry
Or train OpenLLaMA 13B with SuperHOT + summarization data using QLORA.
-
Finetune MPT-30B using QLORA
BTW. they finally merged a MPT patch to work with lora: https://github.com/mosaicml/llm-foundry/issues/304
- [N] Meet MPT-30B: A Fully OpenSouce LLM that Outperforms GPT-3 - Dr. Mandar Karhade, MD. PhD.
-
MPT-30B QLoRA on 24 GB VRAM
Did you run into this error while using qlora on MPT30b?: https://github.com/mosaicml/llm-foundry/issues/413
-
MosaicML Agrees to Join Databricks to Power Generative AI for All
Yes? Their github is under Apache, their base model is under apache, the training data is not theirs, and they provide scripts how to convert it for the pretrain step. They have scripts for pretraining and finetuning as well. Basically for everything.
-
Best model for commercial use?
mosaicml/llm-foundry: LLM training code for MosaicML foundation models (github.com)
-
MosaicML launches MPT-30B: A new open-source model that outperforms GPT-3
MosaicML, a company that provides a platform for training and deploying large language models (LLMs), has recently released its second open-source foundation model called MPT-30B. The model is part of the MosaicML Foundation Series and comes after the smaller MPT-7B model that was launched in May 2023.
What are some alternatives?
Cockatrice - A cross-platform virtual tabletop for multiplayer card games
qlora - QLoRA: Efficient Finetuning of Quantized LLMs
docker-mtgo - Docker image with ready-to-play MTGO (Magic Online) for Linux and macOS
basaran - Basaran is an open-source alternative to the OpenAI text completion API. It provides a compatible streaming API for your Hugging Face Transformers-based text generation models.
magarena - Magarena is a single-player fantasy card game played against a computer opponent.
RasaGPT - 💬 RasaGPT is the first headless LLM chatbot platform built on top of Rasa and Langchain. Built w/ Rasa, FastAPI, Langchain, LlamaIndex, SQLModel, pgvector, ngrok, telegram
HattrickOrganizer - Assistant for Hattrick online football manager
LMFlow - An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
PacketProxy - A local proxy written in Java
prompt-engineering - ChatGPT Prompt Engineering for Developers - deeplearning.ai
mtg-deck-builder - Magic: The Gathering (MTG) deck builder that considers inventory (but not others decks... yet)
llm-numbers - Numbers every LLM developer should know