Add AST (Audio Spectrogram Transformer) Adapter

[dylanberens]

Description

This PR introduces full support for the Audio Spectrogram Transformer (AST) architecture with TransformerLens.

Key Engineering Details
Because AST is built on a ViT-base backbone but processes continuous audio spectrogrmas, several important architectural bridges were necessary:

• Custom ASTEmbed: Implemented a specialized Conv2d embedding layer to handle 1D to 2D tensor reshaping and extract overlapping patches using a stride=(10, 10), which is a frequent cause of disconnects whens working with AST attention weights
• Dual-Token Pooling: Implemented the AST-specific MLP head pooling logic, which averages botht eh CLS and Distillation tokens before classification.
• Dual LayerNorm: Accounted for AST's second LayerNorm applied exclusively to the pooled token prior to the embedding matrix

Adds ast.py (architecture adapter) and test_ast_adapter.py (verifying FP32 mathematical parity with max logit diff < 1e-4).

Fixes # 1484

Type of change

• New feature (non-breaking change which adds functionality)

Checklist:

• I have commented my code, particularly in hard-to-understand areas
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• I have not rewritten tests relating to key interfaces which would affect backward compatibility