PyTorch backend silently accepts shapes/activations the JAX backend rejects (three cases)

The two backends are meant to agree — `convert_and_upload.py` even runs a `verify_parity` step — but the PyTorch side accepts several inputs the JAX side rejects, and does so silently. Three concrete cases, all reproduced on `b15593e4c1111ddb5f4f30dd2957df2edbaa04ca` in a clean container.

**1. `d_model` not divisible by `nhead`**

JAX raises (`tabfm/src/jax/model.py:1148-1151`):

```python
if d_model % nhead != 0:
raise ValueError(f'd_model ({d_model}) must be divisible by nhead ({nhead})')
```

PyTorch just truncates (`tabfm/src/pytorch/model.py:102`): `self.nhead, self.hd = nhead, d_model // nhead`.

```
[torch embed_dim=7 nhead=2 (not divisible)] NO ERROR -> nhead=2 hd=3 -> nhead*hd=6 vs d_model=7
```

The model builds and runs while quietly dropping a dimension.

**2. RoPE dimension**

JAX asserts `dim >= 2` (`jax/model.py:250`). PyTorch's `RoPE.__init__` (`pytorch/model.py:84-87`) has no guard:

```
[Torch RoPE dim=1] NO ERROR -> (1,)
[Torch RoPE dim=0] NO ERROR -> (0,)
[Torch RoPE dim=2 (control)] NO ERROR -> (1,)
```

`dim=0` yields an empty frequency buffer, so the rotation silently becomes a no-op. Note also that `dim=1` and `dim=2` both produce shape `(1,)`.

**3. The supported activation sets differ**

JAX accepts `{relu, gelu, swiglu}` and raises a `ValueError` naming the valid options (`jax/model.py:1153-1155`). PyTorch's `get_activation` (`pytorch/model.py:41-47`) accepts `{relu, gelu, silu}` and raises a bare `KeyError`:

```
[Torch get_activation('silu')] NO ERROR -> silu
[Torch get_activation('swiglu')] KeyError: 'swiglu'
[Torch get_activation('nosuch')] KeyError: 'nosuch'
```

So `silu` works on one backend only, and an unknown name gives a message that does not say what was expected. (`swiglu` is handled earlier via the `self.swiglu` flag, so it works in practice through `MLP` — it is `get_activation` itself that disagrees.)

None of these is urgent, and the default TabFM shapes avoid all three. They matter because the failure mode is silence: a user who mis-specifies a shape gets a subtly wrong model from PyTorch and a clear error from JAX.

Disclosure: I used an AI assistant to help find these. I ran the reproductions myself.

Start with the referenced validation and activation code in tabfm/src/pytorch/model.py, then compare it with the corresponding checks in tabfm/src/jax/model.py. Run the three reproductions in a clean container; done means PyTorch rejects invalid d_model/nhead and RoPE dimensions consistently and reports activation choices in line with the JAX backend.

Written by the indexing model from the issue text.