llm-foundry
AgileRL
llm-foundry | AgileRL | |
---|---|---|
37 | 12 | |
3,730 | 497 | |
4.0% | 3.4% | |
9.7 | 9.8 | |
4 days ago | 5 days ago | |
Python | Python | |
Apache License 2.0 | 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.
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.
AgileRL
- [P] Introducing PPO and Rainbow DQN to our super fast evolutionary HPO reinforcement learning framework
- Introducing PPO and Rainbow DQN to our super fast evolutionary HPO reinforcement learning framework
-
[P] Significant improvements for multi-agent reinforcement learning!
Please check it out! https://github.com/AgileRL/AgileRL
- 10x faster reinforcement learning hyperparameter optimization than SOTA - now with distributed training!
- [P] 10x faster reinforcement learning hyperparameter optimization than SOTA - now with distributed training!
-
(1/2) May 2023
Deep Reinforcement Learning library focused on improving development by introducing RLOps - MLOps for reinforcement learning (https://github.com/AgileRL/AgileRL)
-
[P] 10x faster reinforcement learning HPO - now for RLHF!
https://github.com/AgileRL/AgileRL/blob/main/CONTRIBUTING.md Has a link to our discord too
- 10x faster reinforcement learning HPO - now with CNNs!
- [P] 10x faster reinforcement learning HPO - now with CNNs!
-
[P] Reinforcement learning evolutionary hyperparameter optimization - 10x speed up
GitHub: https://github.com/AgileRL/AgileRL
What are some alternatives?
qlora - QLoRA: Efficient Finetuning of Quantized LLMs
chat-ui - Open source codebase powering the HuggingChat app
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.
RLeXplore - RLeXplore provides stable baselines of exploration methods in reinforcement learning, such as intrinsic curiosity module (ICM), random network distillation (RND) and rewarding impact-driven exploration (RIDE).
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
loopquest - A Production Tool for Embodied AI
LMFlow - An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
de-torch - Minimal PyTorch Library for Differential Evolution
prompt-engineering - ChatGPT Prompt Engineering for Developers - deeplearning.ai
Muzero - Pytorch Implementation of MuZero for gym environment. It support any Discrete , Box and Box2D configuration for the action space and observation space.
llm-numbers - Numbers every LLM developer should know
q-learning-algorithms - This repository will aim to provide implementations of q-learning algorithms (DQN, Double-DQN, ...) using Pytorch.