MarkTechPost · Apr 2
Arcee AI released Trinity Large Thinking, a 400B-parameter sparse MoE reasoning model under Apache 2.0 license optimized for autonomous agents and multi-turn tool use. The model activates only 13B par
Interconnects · Mar 30
NVIDIA's Nemotron-3-Super-120B arrives with 120B params (12B active), 1M context window, and LatentMoE architecture—alongside fresh releases from Sarvam, Cohere, and others spanning OCR, transcription
Simon Willison · Mar 30
Trip Venturella released Mr. Chatterbox, a 340M-parameter language model trained entirely on 28,000 out-of-copyright Victorian texts (1837–1899) from the British Library, weighing just 2GB and runnabl
GitHub Trending · Mar 17
vLLM hits GitHub Trending with state-of-the-art LLM inference performance: continuous batching, speculative decoding, FlashAttention integration, and support for multiple quantization schemes (AWQ, GP
GitHub Trending · Mar 17
LlamaFactory lets you fine-tune 100+ LLMs and vision models through a single unified API and web UI, cutting implementation time from weeks to hours. ACL 2024 paper + Docker support + HuggingFace inte
GitHub Trending · Mar 17
RAGFlow fuses retrieval-augmented generation with agent capabilities to build a context layer for LLMs, offering pre-built templates and a streamlined workflow for enterprises to convert complex data
Analytics Vidhya · Mar 19
1000+ production-ready Claude agent skills are scattered across 5 GitHub repositories that developers can fork instead of building from scratch—a curated shortcut for engineers extending Claude's capa
KDnuggets · Mar 5
A roundup of 10 GitHub repositories that teach system design fundamentals through code examples and documentation. Covers distributed systems patterns, scalability trade-offs, and architectural patter