Pin the Hugging Face revision when loading pretrained weights

Both `load()` paths fetch the pretrained weights from Hugging Face without asking for a particular revision, so each call resolves to whatever `main` points at at that moment:

- PyTorch — `tabfm/src/pytorch/tabfm_v1_0_0.py:157`
- JAX — `tabfm/src/jax/tabfm_v1_0_0.py:279-280`

`revision` is already threaded through `_from_pretrained` in both files, so the plumbing exists — it is simply never given a value, and there is no checksum either.

`main` on `google/tabfm-1.0.0-pytorch` has moved ten times, and one of those commits changed the weight format outright:

```
702835545c8c 2026-07-02 convert weights to safetensors (#3)
```

That is the same change behind callers looking for `pytorch_model.bin` and not finding it, which is what #53 and #77 are about. Anyone who had pinned a revision would have kept working across that day and could then have moved deliberately.

Two things a pin would buy you:

- **Reproducibility** — a given tabfm version resolves to the same weights every time, so a result from three months ago can be reached again.
- **Integrity** — users are not moved onto different weights without noticing.

I have not sent a patch, because deciding *which* commit is the blessed one is your call and I would only be guessing. If it helps, the current head is `77cb9cc1b4fd`, and the shape would be a module-level constant passed as `revision=` in both loaders, still overridable by the caller.

Glad to send the PR once you say which revision it should be.

Disclosure: I used an AI assistant while looking into this. I checked the file references and the Hugging Face commit list myself.

Read the PyTorch loader at tabfm/src/pytorch/tabfm_v1_0_0.py:157 and the JAX loader at tabfm/src/jax/tabfm_v1_0_0.py:279-280, then trace _from_pretrained in both files. Review the Hugging Face commit history and confirm the maintainer-selected blessed revision. Done means both load paths use that revision while still allowing caller overrides.

Written by the indexing model from the issue text.