DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to build a dialect routing study on your own task with CLSR MDia

Adapt the MDia lifecycle to your own dataset and model providers to test budgeted dialect routing.

Short answer: Clone the repository and complete the toy pipeline setup with python -m pip install -e; then read the extension interfaces in docs/extending.md and write dataset and provider adapters for your task and models; copy configs/toy_mdia.yaml to a new config file and point it at your adapters and held-out splits. All steps.

  • Research
  • Advanced
  • 2 hours
  • From the README
  • Any agent

Who it is forAn ML engineer or researcher with a task and access to several LLMs who wants to know whether compact reasoning dialects can cut tokens without losing accuracy.

The problemShorter reasoning traces can drop state a listener needs, so savings must be checked per speaker, listener, and task.

The outcomeA profiled dialect bank and budgeted route plans for your task, with accuracy, token, and parse-risk results recorded per run.

What you need first

  • Python 3.10+ for the offline toy pipeline, or Python 3.11+ for the release reproduction
  • A terminal and git for cloning the repository
  • No API keys are needed for the toy pipeline or the offline release reproduction
  • For new model inference, benchmark inputs from their original sources and provider access (see docs/extending.md)

Steps

  1. Clone the repository and complete the toy pipeline setup with python -m pip install -e ..
  2. Read the extension interfaces in docs/extending.md and write dataset and provider adapters for your task and models.
  3. Copy configs/toy_mdia.yaml to a new config file and point it at your adapters and held-out splits. (inferred, check the README)
  4. mdia collect --config <your-config.yaml> (inferred, check the README)
  5. mdia create --config <your-config.yaml> (inferred, check the README)
  6. mdia evolve --config <your-config.yaml> (inferred, check the README)
  7. mdia profile --config <your-config.yaml> (inferred, check the README)

Prompt for your agent

Using the CLSR_MDia repository, read docs/extending.md and implement a dataset and provider adapter for <target task and model>. Run the mdia collect, create, evolve, and profile stages with a new config file, then report the transfer profiles and confirm the frozen dialect bank was written before any held-out execution.

Caveat. The README says the frozen dialects and route policies should be selected from validation evidence before held-out execution, so the study must keep splits separate or the results will not be valid.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for Plab-Lead/CLSR_MDia and "Build a dialect routing study on your own task"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer