fix: Missing get_input_embeddings / set_input_embeddings on NomicBertModel

NomicBertModel doesn't implement `get_input_embeddings()` or `set_input_embeddings()`, so the transformers fallback in `EmbeddingAccessMixi` tries to resolve them automatically. This fails because:
- `_input_embed_layer` defaults to `embed_tokens`, but NomicBERT uses `word_embeddings`
- `base_model_prefix = "model"`, but `__init__` creates `self.embeddings`, not `self.model`

Adding these two methods fixes this.

modeling_hf_nomic_bert.py

@@ -1890,6 +1890,12 @@ class NomicBertModel(NomicBertPreTrainedModel):
 
         self.apply(partial(_init_weights, initializer_range=config.initializer_range))
 
+    def get_input_embeddings(self):
+        return self.embeddings.word_embeddings
+
+    def set_input_embeddings(self, value):
+        self.embeddings.word_embeddings = value
+
     def forward(
         self,
         input_ids=None,