E2E 3B p24-r1: ttt_only_cadence_2_binary_router

This is a weights-only, inference-ready Orbax release of the terminal step-1024 E2E checkpoint.

Hidden size: 2560
Layers: 32
Training sequence length: 8192
Router z coefficient: 0.0001
GTCF: true
Evaluation: NIAH-1: complete, NIAH-2: complete, NIAH-3: complete, LongBenchV2: complete, PG-19: pending_by_policy

PG-19: pending_by_policy is an explicit status, not a numeric score.

Use checkpoint/ as the manager root and restore step 1024 through the project's read-only routed inference loader. The package includes only model_weights; it cannot resume optimizer training.

No tokenizer bytes, optimizer state, data-iterator state, tracking metadata, internal service paths, or raw evaluation samples are included. Use a separately obtained compatible Llama-3-base tokenizer. See LICENSE_NOTICE.md before use or redistribution.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support