Fix UnboundLocalError in TextClassificationModel when return_label_attention_matrix=True with no text_embedder

[Copilot]

Addresses potential UnboundLocalError when return_label_attention_matrix=True but self.text_embedder is None. The variable label_attention_matrix was only initialized inside the text_embedder branch, causing a runtime error when attempting to return it.

Changes

• Initialize label_attention_matrix = None before the text_embedder conditional branch to ensure the variable exists in all code paths

def forward(self, ...):
    encoded_text = input_ids
    label_attention_matrix = None  # ← Added initialization
    if self.text_embedder is None:
        x_text = encoded_text.float()
    else:
        # ... sets label_attention_matrix from text_embed_output
    
    # ... later
    if return_label_attention_matrix:
        return {"logits": logits, "label_attention_matrix": label_attention_matrix}

When text_embedder is None, the returned dict now contains label_attention_matrix: None instead of raising UnboundLocalError.

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

[Copilot]

Just as a heads up, I was blocked by some firewall rules while working on your feedback. Expand below for details.

Warning

Firewall rules blocked me from connecting to one or more addresses (expand for details)

I tried to connect to the following addresses, but was blocked by firewall rules:

• astral.sh
  • Triggering command: /usr/bin/curl curl -LsSf REDACTED (dns block)

If you need me to access, download, or install something from one of these locations, you can either:

• Configure Actions setup steps to set up my environment, which run before the firewall is enabled
• Add the appropriate URLs or hosts to the custom allowlist in this repository's Copilot coding agent settings (admins only)