Helvete-nano
Summary
VTXAI has released Helvete nano, a compact 2B parameter language model designed for unrestricted conversations and creative freedom.
Similar Articles
VectraYX-Nano: A 42M-Parameter Spanish Cybersecurity Language Model with Curriculum Learning and Native Tool Use
Presents VectraYX-Nano, a 42M-parameter decoder-only language model trained from scratch in Spanish for cybersecurity, featuring curriculum learning, native tool invocation via MCP, and a 170M-token corpus. Empirical findings reveal a loss-versus-register inversion and corpus-density artifacts for tool-use capability.
I released Inflect-Nano, an ultra-extreme tiny 4.63m parameter TTS model.
Inflect-Nano, an ultra-extreme tiny 4.63 million parameter text-to-speech model, has been released.
nvidia/Cosmos3-Nano
NVIDIA releases Cosmos3-Nano, an omnimodal world model for Physical AI that generates video, image, audio, and action commands from text, image, video, and action inputs, targeting robotics, autonomous driving, and smart space applications.
@MaximeRivest: nemotron 550b ultra from nvidia just dropped! it's tool calling and standard system prompt is very very very clean and …
NVIDIA released Nemotron 550B Ultra, a large language model featuring a clean XML-based tool calling interface instead of JSON schemas, with tool results delivered as user messages in XML tags.
NVIDIA has released Nemotron-TwoTower-30B-A3B-Base-BF16, an unusual diffusion-based language model built from the Nemotron 3 Nano 30B-A3B backbone.
NVIDIA released Nemotron-TwoTower-30B-A3B-Base-BF16, a diffusion-based language model that uses block-wise autoregressive diffusion to generate text by iterative denoising of token blocks, achieving 2.42× the generation throughput of the autoregressive baseline while retaining 98.7% of benchmark quality.