Locara

Classical NLP tasks (covered by chat LLM)

HF tasks: text-classification, token-classification, question-answering, zero-shot-classification, table-question-answering, fill-mask. Status: ⛔ not first-class modalities in Locara.

What they are

The pre-LLM era of NLP: BERT-fine-tuned classifiers, NER taggers, extractive QA, NLI-based zero-shot, table-grounded QA, masked LM. Each is a tractable open-weight model and HuggingFace has a rich catalogue, but a modern chat LLM with the right prompt covers all of these tasks well enough that specializing isn’t worth the surface area.

Representative open-weight models (for completeness)

TaskModelParamsLicenseNotes
Text classificationDistilBERT, RoBERTa-Large, DeBERTa-V3-Large60-300 MMIT/Apache-2.0Fine-tune for any classification task.
NER (token classification)spaCy NER, BERT-base-NER, GLiNER110-300 MMITGLiNER is open-vocabulary (zero-shot NER).
Extractive QADeBERTa-v3-Large-SQuAD300 MMITFoundational.
Zero-shot classificationbart-large-mnli, DeBERTa-v3-Large-NLI400 MMITNLI-based.
Table QATaPas-large, TAPEX110-400 MApache-2.0Specialized; heavy.
Fill-maskBERT, RoBERTa110-340 MApache-2.0Internal use only.

Why Locara doesn’t first-class these

A chat LLM (Qwen3-1.7B+) running through text-to-text:

  • Handles every task above with simple prompts.
  • Has flexibility a fixed-class classifier doesn’t (zero-shot generalization, multi-task inference, free-form output).
  • Costs the same RAM whether it answers a single question or classifies 1000 inputs.

The exception would be apps where:

  • Latency: a 100M-param classifier is 30× faster than a 1.5B LLM for batch classification.
  • Determinism: extractive QA is deterministic against a passage; LLM Q&A can hallucinate.
  • Privacy budget: classifiers don’t see context beyond their input; LLM “remembers” via in-context tokens.

If a reference app emerges where these matter, we can revisit.

What Locara has today

⛔ Nothing dedicated. Implicit support via text-to-text.

See also