Spaces:

AdithyaSK
/

scaling-rl-for-llms-amd-ai-dev-day

Running

App Files Files Community

scaling-rl-for-llms-amd-ai-dev-day / index.html

AdithyaSK HF Staff

Deploy Scaling RL for LLMs deck (AMD AI Dev Day)

88369c2 verified 19 days ago

Raw

History Blame Contribute Delete

2.36 kB

	<!doctype html>
	<html lang="en">
	<head>
	<meta charset="UTF-8" />
	<meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1.0, user-scalable=no" />
	<title>Scaling RL for LLMs — Adithya S Kolavi</title>
	<meta
	name="description"
	content="Scaling RL for LLMs: RL Environments and RL Training — a talk by Adithya S Kolavi at AMD AI Dev Day."
	/>
	<meta name="theme-color" content="#07090f" />

	<!-- Social preview. og:image must be absolute, so it points at the deployed
	Space; public/og.png is regenerated by scripts/make_og.py. -->
	<meta property="og:type" content="website" />
	<meta property="og:site_name" content="Scaling RL for LLMs" />
	<meta property="og:url" content="https://adithyask-scaling-rl-for-llms-amd-ai-dev-day.static.hf.space/" />
	<meta property="og:title" content="Scaling RL for LLMs — RL Environments and RL Training" />
	<meta
	property="og:description"
	content="A talk by Adithya S Kolavi at AMD AI Dev Day: what an RL environment actually is, how reward hacking happens, and how to build and train your own with OpenEnv + TRL."
	/>
	<meta property="og:image" content="https://adithyask-scaling-rl-for-llms-amd-ai-dev-day.static.hf.space/og.png" />
	<meta property="og:image:width" content="1200" />
	<meta property="og:image:height" content="630" />
	<meta property="og:image:alt" content="Scaling RL for LLMs — RL Environments and RL Training · Adithya S Kolavi" />

	<meta name="twitter:card" content="summary_large_image" />
	<meta name="twitter:site" content="@AdithyaSK" />
	<meta name="twitter:creator" content="@AdithyaSK" />
	<meta name="twitter:title" content="Scaling RL for LLMs — RL Environments and RL Training" />
	<meta
	name="twitter:description"
	content="A talk by Adithya S Kolavi at AMD AI Dev Day: what an RL environment actually is, how reward hacking happens, and how to build and train your own with OpenEnv + TRL."
	/>
	<meta name="twitter:image" content="https://adithyask-scaling-rl-for-llms-amd-ai-dev-day.static.hf.space/og.png" />
	<script type="module" crossorigin src="./assets/index-BaIqJAjN.js"></script>
	<link rel="stylesheet" crossorigin href="./assets/index-DlQWIdL0.css">
	</head>
	<body>
	<div id="root"></div>
	</body>
	</html>