-
Areas of Interest : GenAI x Reinforcement Learning x Software Engineering
-
At Present : Intern at IIT Delhi : Reinforcement Learning and Robotic Navigation.
-
Currently learning : RAG Evaluation and Optimization strategies, Transformer Architecture and Reinforcement Learning.
-
Currently Building : Making a small language model from scratch [DONE | onto further upgrades] and a implementing Corrective RAG with HyDe and Query decomposition functionality [ONGOING]
-
Future Projects : Fine-tuning Llama-3.2-1B for classification [VERY FUN]
-
Ask me about : Tech, Coffee, Music, Cats, Rubik's cube (PR : 20.77 Seconds), Pizzas and Neovim (btw)
-
Portfolio : mehul.xyz
-
Resume : link
-
Mail : mehulanand.work@gmail.com
-
Blog : substack
🎯
Locked In
CS | Dev x AI | RL - IIT Delhi | Ex-Frontend Sustain Mall
-
IIT Delhi
- Delhi , India
-
23:34
(UTC +05:30) - mehul.xyz
- @mehul_xyz
- in/mehulxyz
- https://mehulanand.substack.com
Pinned Loading
-
smol_LM
smol_LM PublicDone with the implementation, would work on improvising this later :)
Jupyter Notebook
-
-
-
-
-
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.


