रिसर्च पेपर, हिंदी में

Learn machine-learning papers in Hindi.

Watch a short Hindi video on the paper and another on the tool, check yourself with a quick quiz — then build something with what you learned.

Start learning YouTube channel ↗

  1. 1Watch & readA Hindi video, then the paper with a guide.
  2. 2ConceptsThe few ideas you should be able to explain.
  3. 3Quick quizTwo minutes to check it really landed.
  4. 4ActionA small hands-on task with a real result.

Track 1 · 9 steps

Fine-tune Qwen for GST

Take a small open Qwen model and make it measurably better at reasoning about Indian GST than it is out of the box — on a free Colab GPU, with the data, the model and the scores published on Hugging Face.

Start this track → 0 of 9 steps done

Papers in this track

  1. LoRA

    Fine-tune by adding a small low-rank update, not rewriting the model.

  2. QLoRA Hindi video coming soon

    Freeze the base in 4-bit, train adapters on top — a fine-tune on the GPU you already have.

  3. LIMA Hindi video coming soon

    A thousand carefully chosen examples can be enough.

  4. Textbooks Are All You Need Hindi video coming soon

    Better data beats a bigger model.

  5. Self-Instruct Hindi video coming soon

    Bootstrap thousands of training examples from a handful of seeds — and inherit the generator's mistakes if you do not filter.

  6. Quality, Diversity, Complexity Hindi video coming soon

    A survey of what actually makes synthetic data useful — three properties that pull against each other.

  7. Evol-Instruct (WizardLM) Hindi video coming soon

    Make a question harder on purpose — add a constraint, a reasoning step, a rarer case.

  8. RAFT Hindi video coming soon

    Train the model with the right document mixed in among distractors, so it learns to pick.

  9. Agentic Adversarial QA 2026 Hindi video coming soon

    Generate the questions where a weak model and a strong model disagree — a small set aimed at interpretive reasoning.

  10. QueST Hindi video coming soon

    Train the question generator itself to produce difficult problems.

  11. InstructGPT Hindi video coming soon

    The three-step template every assistant follows — demonstrations, preferences, RL.

  12. Tulu 3 Hindi video coming soon

    A full post-training recipe, published — every stage, every dataset.

  13. DPO Hindi video coming soon

    Learn from "this answer is better than that one" — without a reward model.

  14. Distillation Hindi video coming soon

    Teaching a small model to think like a big one.

  15. Who Judges the Judge? 2026 Hindi video coming soon

    An LLM judge's verdict shifts with which model wrote the answer — validate it against an expert first.

  16. DeepSeek-R1 Hindi video coming soon

    Reasoning trained by reinforcement — the model is rewarded for results, not shown answers.

  17. Rubric rewards with GRPO 2026 Hindi video coming soon

    Reinforcement fine-tuning of a quantized Qwen with LoRA, scored criterion by criterion against a rubric.

  18. Rethinking Rubric Generation 2026 Hindi video coming soon

    A vague rubric gives a vague reward — how to split criteria until they actually separate good from bad.

  19. Small Models as Rubric Judges 2026 Hindi video coming soon

    The judge runs thousands of times during RL — a small one can be good enough and far cheaper.

  20. Judge-R1 2026 Hindi video coming soon

    A legal system that pairs agentic retrieval of statutes with rubric-guided RL to cut invented citations.

Hands-on lessons in this track

  1. Build a small eval and an LLM judge Hindi video coming soon

    Turn your failure types into test questions, and check a judge against an expert before you trust its scores.

  2. Your first Unsloth notebook on Colab Hindi video coming soon

    Run a complete LoRA fine-tune end to end and know what each cell is doing.

  3. Pick a Qwen size and load it in 4-bit Hindi video coming soon

    Choose the largest model your GPU can train, and measure its memory instead of guessing.

  4. Chat templates — the format the model expects Hindi video coming soon

    Render a conversation into the exact text and special tokens Qwen was trained on.

  5. Generate a dataset and push it to the Hub Hindi video coming soon

    Go from a few seed examples to a few hundred generated ones, inspect them, and publish the set.

  6. The training run — settings and the loss curve Hindi video coming soon

    Set the handful of numbers that matter, read the loss curve, and fix the usual failures.

  7. Train on preference pairs, then run the model on your laptop Hindi video coming soon

    Turn expert corrections into DPO training data, and export the result to GGUF.

Track 2 · 9 steps

Faster RAG with Opus and Sonnet

Build a retrieval-augmented GST assistant, measure it honestly, then make it faster and cheaper without making it worse — by sending each question to the smallest Claude model that can handle it and not paying twice for the same tokens.

Start this track → 0 of 9 steps done

Papers in this track

  1. RAFT Hindi video coming soon

    Train the model with the right document mixed in among distractors, so it learns to pick.

  2. Judge-R1 2026 Hindi video coming soon

    A legal system that pairs agentic retrieval of statutes with rubric-guided RL to cut invented citations.

  3. RAG Hindi video coming soon

    The original — look up passages first, then generate from them.

  4. Dense Passage Retrieval Hindi video coming soon

    Find passages by meaning, not shared words — the idea behind every embedding search.

  5. RAGAS Hindi video coming soon

    Score a RAG system in parts — was the right text found, and did the answer stick to it?

  6. How Much Do Legal RAG Systems Still Hallucinate? 2026 Hindi video coming soon

    Eight legal RAG systems measured claim by claim — and questions with a false premise are where they break.

  7. RouteLLM Hindi video coming soon

    A small router decides which model answers each question.

  8. Hybrid LLM Hindi video coming soon

    Predict how hard the query is; send only the hard ones to the big model.

  9. FrugalGPT Hindi video coming soon

    Run the cheap model first — then check its work.

  10. AutoMix Hindi video coming soon

    Let the small model grade its own answer against the retrieved context.

  11. RouterBench Hindi video coming soon

    One ruler for every router — and a humbling result.

  12. Temporal Misgrounding in Legal RAG 2026 Hindi video coming soon

    Tax-law RAG keeps citing today's version of a provision when the question is about another date.

  13. The Token Tax 2026 Hindi video coming soon

    Retrieve a few passages, or load every document into the prompt? An accuracy-versus-cost comparison.

  14. LLMs for Austrian VAT Law Hindi video coming soon

    Fine-tuning and RAG compared head to head on real VAT cases from a tax firm — the closest study to this project.

Hands-on lessons in this track

  1. Build a baseline RAG pipeline Hindi video coming soon

    Chunk the documents, embed them, retrieve, and answer with Claude — the plain version you will later speed up.

  2. Evaluate RAG in two halves Hindi video coming soon

    Measure whether the right passage was found, and separately whether the answer stuck to it.

  3. Prompt caching and batch processing with Claude Hindi video coming soon

    Stop paying, and waiting, for the same long prompt again and again.

This site is an experiment in learning in public — its author is the first student. Want to go deeper? Browse all illustrated papers, the illustrated decoder, or the blog.