hipsters out there using gpt-2
SOFTWARE
-
ESPnet-SpeechLM: Open Source Speech Language Model Toolkit
By
–
ESPnet-SpeechLM: An Open Speech Language Model Toolkit ESPnet-SpeechLM is an open-source toolkit for developing Speech Language Models (SpeechLMs) and voice-driven applications. It simplifies speech processing by framing tasks as sequential modeling problems, automating data
-
Cost-Efficient Collaboration Between On-Device and Cloud Language Models
By
–
Minions: Cost-efficient Collaboration Between On-device and Cloud Language Models This paper explores a cost-efficient collaboration between small, on-device language models (LMs) and large, cloud-hosted LMs for data-intensive tasks. The MinionS protocol improves task
-
SWE-RL: Enhancing LLM Reasoning Through Software Evolution
By
–
SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution SWE-RL is a reinforcement learning (RL) approach that enhances LLM reasoning for software engineering by learning from open-source software evolution data. It trains Llama3-SWE-RL-70B on GitHub
-
Building Production-Ready RAG Systems with Qdrant FastAPI
By
–
RAG Pipeline Guide Learn to build production-ready RAG systems using Qdrant vector DB, FastAPI, and LangChain's LCEL for sophisticated retrieval chains. Key features:
– Async vector search
– Type-safe FastAPI endpoints
– LCEL RAG pipelines Start building better RAG systems! -
MIT’s ‘Introduction to Algorithms’ Celebrates 30 Years As Premier CS Text
By
–
MIT’s “Introduction to Algorithms,” published #otd in 1990, is the world’s most cited CS text, with 67K citations & over a million copies sold. https://
bit.ly/3y1yMPR @mitpress -
Omi AI Wearable: Open-Source Device for Real-Time Transcription
By
–
Omi AI Wearable An open-source wearable device that transforms conversations into real-time transcriptions using LangChain's AI capabilities. Features on-device processing and full iOS/Android support. Check out Omi now! https://
github.com/BasedHardware/
omi
… -
Modular Design: Essential Skill for Highly Productive People
By
–
Highly productive people know what modular design is and how to use it.
-
CodeLLM Major Upgrade: Fast Autocomplete, Thinking Agents, SOTA Performance
By
–
CodeLLM got a huge upgrade yesterday
— Abacus.AI (@abacusai) 1 mars 2025
– blazingly fast autocomplete
– sonnet thinking for agents
– SOTA coding agent
– multiple UX improvement and bug fixes pic.twitter.com/TSzUEE3kf6CodeLLM got a huge upgrade yesterday – blazingly fast autocomplete – sonnet thinking for agents – SOTA coding agent – multiple UX improvement and bug fixes
-
T_Priority Technology Enhances Critical Communication for NYC Heroes
By
–
It’s impressive to see how technology like @T_Priority is making such a real-world impact, especially for our everyday heroes.
— Antonio Grasso (@antgrasso) 1 mars 2025
Kudos to @NicoleHudnet and the entire team for ensuring reliable communication in critical situations.#TPriorityxNYC https://t.co/P3OgfhrUPoIt’s impressive to see how technology like @T_Priority is making such a real-world impact, especially for our everyday heroes. Kudos to @NicoleHudnet and the entire team for ensuring reliable communication in critical situations. #TPriorityxNYC