OPEN SOURCE

→ View original post on X — @localghost

Open Sourcing as Norm for AI Adoption and Trust

By

@localghost

–

11 December 2023 20h32

I guess there’s not many provable options other than maybe open sourcing. Seems like it’s the norm though, so maybe people are willing to do this for now.

→ View original post on X — @langchain

Mistral 7B RAG Production Deployment with LangServe

By

@langchain

–

11 December 2023 20h28

Deploying Mistral-7B RAG to Production Join our friends at @AIMakerspace to learn how to go from prototype to production with LangServe and Mistral 7B! Will cover LCEL, HuggingFace, LangServe, LangSmith This Thursday, 10am PST Link:

→ View original post on X — @langchain

Learning Qdrant Vector Database Integration with LangChain

By

@langchain

–

11 December 2023 20h13

If you want to learn how to use @qdrant_engine with LangChain, check out this session with @LukawskiKacper
!

→ View original post on X — @langchain

RAG Optimization with LangChain and Vespa Streaming

By

@langchain

–

11 December 2023 17h42

Turbocharge RAG with LangChain and Vespa Streaming Mode for Sharded Data @vespaengine
's streaming search solution enables you to efficiently search over sharded data – perfect for when you want to store data grouped by user id @jobergum wrote a great article (complete with

Mixtral Details and La plateforme Developer Platform Launch

By

–

11 December 2023 15h20

More details about Mixtral can be found at https://
mistral.ai/news/mixtral-o
f-experts/
… We are also very happy to announce "La plateforme" our early developer platform (in beta & limited access), to access our models through our API: https://
mistral.ai/news/la-platef
orme/
… (7/n)

Mixtral Outperforms Llama 2 70B on European Language Benchmarks

By

–

11 December 2023 15h20

Mixtral has been trained on a lot of multilingual data and significantly outperforms Llama 2 70B on French, German, Spanish, and Italian benchmarks. (4/n)

Mixtral outperforms Mistral 7B in science, mathematics, and code

By

–

11 December 2023 15h20

Compared to Mistral 7B, Mixtral is significantly stronger in science, in particular in mathematics and code generation. (5/n)

Mixtral: 12B Speed with 45B Parameter Access via Expert Selection

By

–

11 December 2023 15h20

Even though each token only sees two experts, the selected experts can be different at each timestep. As a result, Mixtral decodes at the speed of a 12B model, while effectively having access to 45B parameters. (3/n)

Mixtral 8x7B: Open Weight Mixture of Experts Model Released

By

–

11 December 2023 15h20

Very excited to release our second model, Mixtral 8x7B, an open weight mixture of experts model.
Mixtral matches or outperforms Llama 2 70B and GPT3.5 on most benchmarks, and has the inference speed of a 12B dense model. It supports a context length of 32k tokens. (1/n)