Model Detail
MOSS-TTS-v1.5
—MOSS-TTS-v1.5 is a code generation model with 4.2B parameters released by OpenMOSS-Team. The model is registered under the text-to-speech pipeline tag on Hugging Face, distributed under the permissive apache-2.0 license.
MOSS-TTS-v1.5 ships with 4.2B parameters. Total weight footprint is approximately 8.5 GB, which is the relevant figure when planning local-inference VRAM. The apache-2.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.
Downloads of MOSS-TTS-v1.5 have moved +420.1% over the trailing seven days. That puts the model in active uptrend territory; a sustained move of this size usually reflects a recent release, a viral integration, or a benchmark surprise rather than steady-state demand. These numbers are signal, not guarantee — week-over-week download counts on Hugging Face also reflect mirror traffic, CI scrapes, and one-off benchmarking runs.
MOSS-TTS-v1.5 is best fit for code completion, repository-scale Q&A, and pair-programming integrations. It is a less obvious choice for one-shot generation of security-critical code without review. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
MOSS-Audio Technical Report
arXiv:2606.01802v2 Announce Type: replace-cross Abstract: MOSS-Audio is a unified audio-language model for speech, environmental sound, and music understanding, supporting audio captioning, time-aware question answering, timestamped transcription, and audio-grounded reasoning. MOSS-Audio couples a d
Rel-MOSS: Towards Imbalanced Relational Deep Learning on Relational Databases
arXiv:2603.07916v2 Announce Type: replace Abstract: In recent advances, to enable a fully data-driven learning paradigm on relational databases (RDB), relational deep learning (RDL) is proposed to structure the RDB as a heterogeneous entity graph and adopt the graph neural network (GNN) as the predi
MoSSP: A Momentum-Based Single-Loop Stochastic Penalty Method for Nonconvex Constrained DC-Regularized Optimization
arXiv:2605.29635v1 Announce Type: cross Abstract: In this paper, we study a structured class of nonconvex constrained stochastic problems with difference-of-convex (DC) regularization, where the feasible set is possibly nonconvex and the concave part of the DC regularizer is allowed to be nonsmooth.
MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems
arXiv:2605.22794v2 Announce Type: replace Abstract: Autonomous agentic systems are largely static after deployment: they do not learn from user interactions, and recurring failures persist until the next human-driven update ships a fix. Self-evolving agents have emerged in response, but all confine
