Did you know that Replicate has speech-to-text models for transcribing audio? They're actually super good, thanks to the open source community. Like not to brag but this model runs 9x faster and 10x cheaper than OpenAI's Whisper API. That's kinda crazy
OPEN SOURCE
-
Dataherald: Open-Source Leader in Text-to-SQL Technology
By
–
How Dataherald Makes Natural Language to SQL Easy Text-to-SQL is a HUGE use case, and @DataheraldCo is the open-source leader in the space This is a great look behind the curtains to see what makes it tick. Blog: https://
blog.langchain.dev/dataherald/ -
OSS Retrieval Agent with LangChain and Mistral AI
By
–
📖 OSS Retrieval Agent for your Documents 🎥
— LangChain (@LangChain) 14 février 2024
Dive into LangChain Founding Engineer @eyfriis 's latest video showcasing a build with the `retrieval-agent-fireworks` template.
Supercharge a @MistralAI (hosted on @FireworksAI_HQ) agent with vectorstore retrieval using @nomic_ai… https://t.co/3dN6Geicn3 pic.twitter.com/LsD2Uk0CLaOSS Retrieval Agent for your Documents Dive into LangChain Founding Engineer @eyfriis 's latest video showcasing a build with the `retrieval-agent-fireworks` template. Supercharge a @MistralAI (hosted on @FireworksAI_HQ
) agent with vectorstore retrieval using @nomic_ai -
7B Model Achieves 1M Context Window with RingAttention
By
–
7B model, 1M context window! Lots of results over long token windows; this looks very promising. https://
largeworldmodel.github.io RingAttention is what makes this works, summary generated by GPT: Ring Attention is a new method that reduces the memory requirements of Transformers. It -
Train Predictive Models with Lightwood: Default and Custom Mixers
By
–
Once you get Python Code for the Problem you can then train the model on the data and run predictions. There are many default available predictive models in Lightwood called "Mixers" but it also supports you to create your custom mixers. Check this: https://
lightwood.io/mixer.html -
Pandas to Python Code Generation via JSON-AI Workflow
By
–
Let's see how this works: Load data in Pandas and define a "ProblemDefinition" via dictionary specifying the name of the target column. Now Create a JSON-AI syntax using "json_ai_from_problem" function From Json AI generate a python code using "code_from_json_ai"
-
Nous Research Launches Hermes 2 Llama-2 70B Model
By
–
Nous Research introduced Hermes 2 Llama-2 70B. It's the org's largest model and is trained on over 1M synthetic data entries, also featuring advanced prompt formats for enhanced dialogue interaction.
-
Nvidia Chat with RTX: Free Local AI Chatbot for Open-Source Models
By
–
Nvidia released Chat with RTX, a free AI chatbot that can run leading open-source models locally.
— Rowan Cheung (@rowancheung) 14 février 2024
Chat with RTX can:
– Snalyze process responses based on a users files and data
– Integrate data from YouTube videos and playlists
– Run without internet https://t.co/jfT3kvDryiNvidia released Chat with RTX, a free AI chatbot that can run leading open-source models locally. Chat with RTX can:
– Snalyze process responses based on a users files and data
– Integrate data from YouTube videos and playlists
– Run without internet -
Open Source AI Community Recognition and Appreciation
By
–
you are underrated (and the whole open-source AI community)
-
DP-Auditorium: Open Source Differential Privacy Auditing Library
By
–
Introducing DP-Auditorium, an open source library for auditing #DifferentialPrivacy guarantees with just black-box access to a mechanism, i.e., without any knowledge of the mechanism’s internal properties. Learn more and copy the code. ↓ https://
goo.gle/42GW63S