Going to open-source the most token-intensive project I've ever built tomorrow If enough people try it, it'll probably double the use of the Claude 3 API within a day 🙂
OPEN SOURCE
-
Apache 2 License Attribution for AI Software Code
By
–
That is fantastic! Thank you so much for that, will credit you if I include it in any software, are you OK with Apache 2 license for your code?
-
Working MLX Code Examples for AI Implementation
By
–
Sounds promising – have you seen working MLX code that uses it?
-
Local AI Models via pip Installation Without External Server
By
–
I'm looking for stuff I can cleanly "pip install" without having to run an additional server – ollama is my backup plan if I can't solve it without
-
Running LLaVA 1.6 Locally on Mac: Python Recipe Guide
By
–
Does anyone have a good Python recipe for running LLaVA 1.6 on a Mac? Any library you like is fine but I don't want to have to run a separate server process
-
License breach implications for AI monetization models
By
–
My guess is that if anyone is making money they're in breach of the license
-
llm-command-r 0.2 Adds Websearch Connector for Cohere Models
By
–
Here's llm-command-r version 0.2, which adds support for the websearch connector, an option which allows the Cohere models to run a web search and use the results from that as part of the context for answering the prompt https://
github.com/simonw/llm-com
mand-r/releases/tag/0.2
… -
Record Manager: Maintaining Updated Vector Embeddings in RAG
By
–
Upserting documents to vector database is the key of building a RAG solution.
— FlowiseAI (@FlowiseAI) 4 avril 2024
❓But.. how to maintain an up-to-date vector embeddings with updated documents?
🗄️Record Manager! Document chunks will be hashed, stored and compared to prevent duplication
Available in 1.6.3! pic.twitter.com/dQzkTrn9SlUpserting documents to vector database is the key of building a RAG solution. But.. how to maintain an up-to-date vector embeddings with updated documents? Record Manager! Document chunks will be hashed, stored and compared to prevent duplication Available in 1.6.3!
-
Cohere releases Command R+ LLM with 128k context, multi-language support, and tool use
By
–
New Command R+ from Cohere — 128k context, open weights for non-commercial use, commercial API priced similar to Claude 3 Sonnet Tokenizer is designed to be efficient in 10 languages so definitely consider for non-English text. Multi-hop tool use sounds interesting too
-
DBRX Instruct Open Source Model Launches on Poe Platform
By
–
New on Poe: DBRX Instruct! This leading-edge open source model excels at a wide range of tasks, including language understanding, programming, logic, and math, and has been fine-tuned to specialize in few-turn interactions. (1/2)