Supreeth Rao

Supreeth

·

https://supreethrao.com

AI & ML interests

Reinforcement Learning, Large Language Models, Distributed Computing

Recent Activity

upvoted an article 9 days ago

Welcome Inkling by Thinking Machines

updated a bucket 11 days ago

Supreeth/xrpo-repro-artifacts

updated a bucket 11 days ago

Supreeth/xrpo-repro-qwen3-0.6b-gsm8k-bucket

View all activity

Organizations

buckets 2

Supreeth/xrpo-repro-artifacts

Supreeth/xrpo-repro-qwen3-0.6b-gsm8k-bucket

Collections 1

spaces 2

Repro: XRPO: Pushing the Limits of GRPO with Targeted Exploration and Exploitation

Collaborate on a research logbook with an AI coding agent

VeriRL — Verilog RTL Design Environment

Step through a Verirl environment by sending actions and view results

models 13

Supreeth/searchlm-nl2bm25-grpo-v2

Text Generation • 3B • Updated about 1 month ago • 13

Supreeth/searchlm-nl2bm25-grpo

Text Generation • 3B • Updated about 1 month ago • 16

Supreeth/searchlm-nl2bm25-sft-v2

Text Generation • 3B • Updated about 1 month ago • 14

Supreeth/searchlm-nl2bm25-sft

Text Generation • 3B • Updated about 1 month ago • 7

Supreeth/verirl-rlvr-qwen3-4b-thinking

Supreeth/verirl-sft-qwen3-4b-tooluse-merged

Text Generation • 4B • Updated Apr 26 • 35

Supreeth/verirl-sft-qwen3-4b-tooluse

Supreeth/verirl-sft-qwen3-4b-thinking-merged

Text Generation • 4B • Updated Apr 25 • 9

Supreeth/verirl-sft-qwen3-4b-thinking

Supreeth/verirl-rlvr-qwen3.5-4b

datasets 2

Supreeth/xrpo-repro-artifacts

Updated 11 days ago • 70

Supreeth/nl2bm25-sft

Viewer • Updated about 1 month ago • 5.08k • 50