tracecat
megablocks
tracecat | megablocks | |
---|---|---|
2 | 6 | |
2,047 | 1,080 | |
96.9% | 14.1% | |
9.9 | 8.9 | |
7 days ago | 11 days ago | |
TypeScript | 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.
tracecat
megablocks
- FLaNK AI - 01 April 2024
- Mistrsal has released a new 87GM model
-
Megablocks-Public
This is a fork of https://github.com/stanford-futuredata/megablocks
should link to the original when possible, per HN posting guidelines
-
New Mistral models just dropped (magnet links)
I guess with +40 GBs of VRAM (until quantized) and megablocks as run time. https://github.com/stanford-futuredata/megablocks
- MegaBlocks: Efficient Sparse Training with Mixture-of-Experts
What are some alternatives?
speedb - A RocksDB compliant high performance scalable embedded key-value store
DataDreamer - DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤
lapdev - Self-Hosted Remote Dev Environment
zenml - ZenML 🙏: Build portable, production-ready MLOps pipelines. https://zenml.io.
axolotl - Go ahead and axolotl questions
CML_AMP-to-Airgapped - Download the AMP catalog for an offline (airgapped) deployment of the AMP catalog.
graphql-ws - Coherent, zero-dependency, lazy, simple, GraphQL over WebSocket Protocol compliant server and client.
llama_index - LlamaIndex is a data framework for your LLM applications
FLaNK-python-processors - Many processors
MyScaleDB - An open-source, high-performance SQL vector database built on ClickHouse.