GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
marinarosa
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
marinarosa
Model Tree
marinarosa/minicpm5-1b-vivamais-v1
Input Modalities
Output Modalities
Supported Functionality
MiniCPM5-1B Viva Mais text v4, trained from marinarosa/minicpm5-1b-vivamais-v1 with a
broader Brazilian Portuguese conversational and grounded-Q&A mix.
The training package uses a redacted Viva Mais dashboard Q&A replay set, grounding-negative rows, and filtered Rio 3.1 teacher-distilled rows. The v4 variant intentionally excludes the generic WhatsApp-style bucket and uses a stricter final-answer-only teacher prompt. Teacher rows are filtered to reject verbose wrappers and hidden-reasoning artifacts. No raw WhatsApp exports, client identifiers, identity documents, or local private data are published.