Fix CpmAnt loading: size lm_head to vocab_size (#48012)
* Fix CpmAnt loading: size lm_head to vocab_size
The released openbmb/cpm-ant-10b checkpoint ships lm_head.weight with shape
(vocab_size, hidden) = (30720, 4096), bit-identical to the first vocab_size rows
of input_embedding.weight (31744, 4096). The trailing prompt_types *
prompt_length rows are soft-prompt embeddings and are never decoding targets.
The model built the head at vocab_size + prompt_types * prompt_length and
declared a whole-tensor tie to the embedding, so from_pretrained hit a shape
mismatch and then crashed in tie_weights comparing meta tensors.
Size the head to vocab_size, which matches the checkpoint, and drop the
whole-tensor tie mapping that could never have been valid at these shapes.
* Shorten lm_head comment
