/**
 * import/foreign/codestral_mamba.ts — weight port for Codestral-Mamba
 * (`mistralai/Mamba-Codestral-7B-v0.1`, `Mamba2ForCausalLM`,
 * `model_type: "mamba2"`, Mamba-2 / SSD).
 *
 * Source layout confirmed against the repo's published HF `config.json`, its
 * `model.safetensors.index.json` (579 tensors = 9 per layer × 64 + 3 globals),
 * the header of `consolidated.safetensors`, and
 * `transformers/models/mamba2/modeling_mamba2.py`:
 *
 *   backbone.embeddings.weight                    [vocab, d_model]
 *   backbone.layers.{N}.norm.weight               [d_model]
 *   backbone.layers.{N}.mixer.in_proj.weight      [2*d_inner + 2*n_groups*d_state + n_heads, d_model]
 *   backbone.layers.{N}.mixer.conv1d.weight       [conv_dim, 1, d_conv]
 *   backbone.layers.{N}.mixer.conv1d.bias         [conv_dim]
 *   backbone.layers.{N}.mixer.dt_bias             [n_heads]
 *   backbone.layers.{N}.mixer.A_log               [n_heads]
 *   backbone.layers.{N}.mixer.D                   [n_heads]
 *   backbone.layers.{N}.mixer.norm.weight         [d_inner]
 *   backbone.layers.{N}.mixer.out_proj.weight     [d_model, d_inner]
 *   backbone.norm_f.weight                        [d_model]
 *   lm_head.weight                                [vocab, d_model]
 *
 * where `conv_dim = d_inner + 2 * n_groups * d_state`. Mamba-2 has no `x_proj`
 * and no `dt_proj`: B, C and dt all come out of the fused `in_proj`.
 *
 * Three reconciliations against `Mamba2Block`:
 *
 *  1. **`in_proj` row order.** Upstream splits
 *     `[gate (d_inner), x|B|C (conv_dim), dt (n_heads)]`; this engine's fused
 *     projection is `[x (d_inner), B (n_groups*d_state), C (n_groups*d_state),
 *     dt (n_heads)]` — the SAME tail, minus the leading gate rows. So the port
 *     is one contiguous row slice starting at `d_inner`, and the gate rows are
 *     declared as a discard (see 3).
 *  2. **`A_log` convention.** Upstream uses `A = -exp(A_log)`; `ssd.ts` uses
 *     `A = -softplus(A_log)`. The port re-expresses the same `A` as
 *     `softplus⁻¹(exp(A_log))` so decay rates are preserved exactly, rather than
 *     copying the raw value and silently changing every head's decay.
 *  3. **The gate branch.** `Mamba2Block` has no `z` gate: it RMS-norms the scan
 *     output and projects out, where upstream computes
 *     `norm(y * silu(z))`. The `d_inner × d_model` gate rows therefore have no
 *     target. That is a REAL loss of capability, not a formatting detail, and it
 *     is reported as a `PortDiscard` on every layer so a caller sees it.
 *
 * Also mapped without transform: `mixer.norm.weight` → the block's inner
 * `normWeight` (applied ungated here, per 3), `backbone.layers.N.norm.weight` →
 * `preNormWeight`, `conv1d.{weight,bias}` (depthwise, taps reversed) → the fused
 * `[x, B, C]` conv, and `D` / `dt_bias` per head. Linear weights are
 * `[out, in]` row-major on both sides, so no transposes.
 *
 * `tie_word_embeddings: false`, so `lm_head.weight` is a real stored tensor with
 * no target here (`HybridMambaModel` ties its head to the embedding) — it is
 * reported as unmapped.
 */
import { type ForeignMambaAdapter } from "./adapter.js";
export declare const codestralMambaAdapter: ForeignMambaAdapter;
//# sourceMappingURL=codestral_mamba.d.ts.map