Skip to content

Add optional MuRIL and IndicBERT encoder backbones#1766

Open
maziyarpanahi wants to merge 1 commit into
masterfrom
feature/om-669-muril-indicbert-embedding-integration-optional-w
Open

Add optional MuRIL and IndicBERT encoder backbones#1766
maziyarpanahi wants to merge 1 commit into
masterfrom
feature/om-669-muril-indicbert-embedding-integration-optional-w

Conversation

@maziyarpanahi

Copy link
Copy Markdown
Owner

Description

Adds an explicit, user-supplied MuRIL or IndicBERT backbone path for Indic entity adapters. The integration exposes aligned tokenizer outputs and hidden states, keeps existing Hindi and Telugu predictors unchanged, returns deterministic skip reasons when configuration or optional runtime support is absent, and never bundles encoder weights.

Type of Change

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • Documentation update
  • Code refactoring
  • Test addition/improvement

Changes Made

  • Added the stable encoder contract and optional MuRIL/IndicBERT loader with permissive-license metadata and hash-only diagnostics.
  • Added process-local registry configuration, opt-in language discovery, model-card provenance, and encoder license records.
  • Added an offline synthetic Indic recall-delta suite covering native-script and Hinglish paths with zero encoder leakage.

Testing

  • I have added tests that prove my feature works
  • New and existing unit tests pass locally with my changes
  • I have tested this change with different models/inputs

Commands run:

  • .venv/bin/python -m pytest tests/ -q (5,208 passed, 46 skipped)
  • make format
  • make lint
  • make format-check
  • scoped pre-commit run --files ...
  • make docs-build

Documentation

  • I have updated the documentation accordingly
  • I have added docstrings to new functions/classes
  • I have updated the CHANGELOG.md

Code Quality

  • I ran make format, make lint, and make format-check
  • For Swift/OpenMedKit changes, I ran make format-swift and make lint-swift
  • I have performed a self-review of my own code
  • I have commented my code, particularly in hard-to-understand areas
  • My changes generate no new warnings

Dependencies

  • I have not added any new dependencies
  • OR I have added new dependencies and they are justified because: N/A

Checklist

  • I have read the contributing guidelines
  • My commits have clear, descriptive messages
  • I have squashed/organized my commits appropriately

Related Issues

Closes #1495

Screenshots/Examples

Not applicable; this change adds a Python encoder contract, registry integration, tests, and documentation.

@maziyarpanahi maziyarpanahi added roadmap-v2 OpenMed V2 roadmap backlog feature New capability P2 Medium labels Jul 19, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

feature New capability P2 Medium roadmap-v2 OpenMed V2 roadmap backlog

Projects

None yet

Development

Successfully merging this pull request may close these issues.

MuRIL / IndicBERT embedding integration for Indic entity models with optional user-supplied permissive weights

1 participant