- in
- [B batch, T positions, 768 d]
- out
- [B batch, T positions, 768 d]
- parameters
- 2,359,296 · × 3 blocks = 7,077,888
Parameters
2,359,296 parameters per instance, across its learned components
| Component | Calculation | Parameters |
|---|---|---|
| Query, key and value projection | 1,769,472 | |
| Output projection | 589,824 | |
| Per-instance total | 2,359,296 | |
Across 3 independent blocks: parameters.
Derived from the pinned implementation’s constructors and configuration. The checkpoint’s tensors have not been counted. 306,011,162 of these parameters are trained; frozen GPT-2 and the decoder’s mask vector, 124,442,112, are not.
Explanation
Attention is bidirectional: no position is masked.
The token decoder’s blocks set the softcap to 0, which turns it off.
Sources2
Direct evidence
A block owns two gain-only LayerNorms, a fused query–key–value projection and an output projection without bias, an MLP of the configured kind, and, with modulation, an affine layer from the time condition to six vectors, initialized at zero.
The implementation, pinned at revision e18c42acdfb7, not yet public
Direct evidence
A block normalizes, modulates by the time condition’s shift and scale, projects to queries, keys and values, rotates queries and keys, attends over all positions with softcap, and adds the projected output scaled by a gate; the MLP branch does the same with its own shift, scale and gate.
The implementation, pinned at revision e18c42acdfb7, not yet public