Note that this is not the only option to easily use open source models off the shelf For example we also have a Replicate integration: https://
python.langchain.com/en/latest/modu
les/models/llms/integrations/replicate.html
… In general I'm really excited to see more options like this – makes it much easier to experiment with these OSS models!
OPEN SOURCE
-
LangChain Replicate Integration Simplifies Open Source Model Deployment
By
–
-
Accessing Open Source Models via API Made Easy
By
–
My biggest hurdle to using open source models is that I just want to access them behind an API to start At some point I may want to fine tune them, but to start I don't want to worry about hosting – I just want to get started building! @MosaicML makes it easy to do so
-
MosaicML Models Integration with LangChain Platform
By
–
First, you do need to sign up for an account. You can do that here: https://
forms.mosaicml.com/demo?utm_sourc
e=langchain
… They have two types of models, both of which are integrated with LangChain: Text Generation Models: https://
python.langchain.com/en/latest/modu
les/models/llms/integrations/mosaicml.html
… Text Embedding Models: https://
python.langchain.com/en/latest/modu
les/models/text_embedding/examples/mosaicml.html
… -
MosaicML Inference API Integration with LangChain Open Source
By
–
Want to be able to easily access open source models behind an API? @MosaicML has got you covered Excited to announce an integration of their inference API with @langchain
, making it easy to experiment with MPT-7B, Dolly, and embedding models Quick -
Apple PyTorch Support Threatens Nvidia AI Hardware Dominance
By
–
Nvidia has developed a stranglehold on AI development thanks to PyTorch's reliance on Cuda. Apple hardware getting full-fledged support for PyTorch could drastically upend that for an entire subset of AI development focused on smaller, more lightweight models.
-
Running Meta LLaMA Models on MacBook Pro CPU
By
–
Right now you can actually run these models on your MacBook Pro, but it runs on the CPU. And Apple's general support of PyTorch has been dubious at best. But its hardware is VERY good, with more than enough power to run Meta's smaller LLaMA models without even using a GPU.
-
LangChain Updates Retrieval Abstractions Integration Webinar
By
–
Retrieval Webinar A few months ago we changed @langchain abstractions to allow for arbitrary retrieval algorithms I'm excited to learn from @lateinteraction @jobergum @charles_irl which ones we should be implementing/integrating! Sign up
-
Open-Source AI Game Jam: Build Games with AI Tools
By
–
Rules:
• Build any game you want, however you want
• Pre-existing assets, code, and AI allowed
• Use at least one open-source AI tool More info here https://
itch.io/jam/open-sourc
e-ai-game-jam
… -
Open Source AI Game Jam: Create Games in Weekend
By
–
Introducing the Open Source AI Game Jam let’s use AI tools to unlock creativity and make a game in a weekend July 7 to 9 Open to everyone Free to participate Claim Your Spot in the Game Jam https://
itch.io/jam/open-sourc
e-ai-game-jam
… More info in this thread -
Microsoft Data Science Toolkit: Open-Source ML AI Accelerators
By
–
Data Science Toolkit — from Microsoft The data science toolkit is an open-source collection of proven ML and AI implementation accelerators. https://
bit.ly/3pJk92R