Skip to content
View amaljoe's full-sized avatar
☺️
For a better tomorrow
☺️
For a better tomorrow

Highlights

  • Pro

Block or report amaljoe

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
amaljoe/README.md

I'm Amal Joe R S — an AI engineer specializing in LLMs, multimodal models, and reinforcement learning. Currently finishing my M.Tech at IIT Bombay with research at IBM and collaborations with Meta and BharatGen.

Pinned Loading

  1. fms-hf-tuning-with-data-mixing fms-hf-tuning-with-data-mixing Public

    Python

  2. OCR_with_LLMs OCR_with_LLMs Public

    Jupyter Notebook 2

  3. Document-Image-Translation Document-Image-Translation Public

    Forked from mindee/doctr

    docTR (Document Text Recognition) extended with document image translation abilities

    Jupyter Notebook

  4. LLMs-From-First-Principles LLMs-From-First-Principles Public

    Jupyter Notebook

  5. vision-coder vision-coder Public

    Image conditioned code generation using VLM as RL agent.

    Python 1 2

  6. few-shot-distillation few-shot-distillation Public

    We distill the behavior of few-shot in-context learning (ICL) into model parameters. A teacher — the same model running with 8-shot context — produces a richer output distribution at every answer t…

    Python