Read the equation
The query–key matrix product forms similarities between each query position and key position. The prose uses 0.135237 as its attention multiplier. From the displayed exact settings, the multiplier is (1+0.1 ln 40)²/√192≈0.1352337789; the text’s decimal is an approximation. This equation precedes the attention mask and row-wise softmax.
Terms & definitions
| Term | Meaning in this source |
|---|---|
| q | Queries,192 components per head |
| k | Keys,192 components per head |
How it works
Read the definition from its right-hand expression to the quantity on the left. Its surrounding source records the intended input, state, or parameter context. Where the source leaves an operation unspecified, this page preserves that gap.
Assumptions & limits
Source recovery establishes that the expression appears in this record. Its mathematical validity, implementation behavior, and interpretation must be assessed separately. See the linked source and research notes for the checks available for this version.
Original context
Read the surrounding source passage
ATTENTION
q = concat(q_nope, q_rope) -> 192 per head
k = concat(k_nope, k_rope) -> 192 per head (k_rope broadcast to all heads)
scores = q @ k^T * 0.135237
probs = softmax(scores, dim=-1) computed in float32, cast back to q.dtype
out = probs @ v -> 128 per head
out = o_proj(out.reshape(T, 16384)) -> 7168 fp8 (7168, 16384)Exact original notation
scores = q @ k^T * 0.135237