Perusha Moodley's picture

6 8

Perusha Moodley

moodlep

·

https://www.perusha.dev/

AI & ML interests

RL, DRL, Decision Transformers, Auxiliary signals, self-supervised methods

Recent Activity

liked a dataset 10 days ago

Anthropic/hh-rlhf

upvoted a paper 22 days ago

HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs

updated a model 29 days ago

moodlep/smollm2-17b-dpo-cai-v1

View all activity

Organizations

moodlep's activity

liked a dataset 10 days ago

Anthropic/hh-rlhf

Viewer • Updated May 26, 2023 • 169k • 12.6k • 1.26k

liked 4 models about 1 month ago

HuggingFaceTB/SmolLM2-1.7B

Text Generation • Updated 1 day ago • 67.9k • 90

unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit

Text Generation • Updated 5 days ago • 627k • 55

NousResearch/Llama-2-7b-chat-hf

Text Generation • Updated Jun 3, 2024 • 296k • 184

unsloth/mistral-7b-v0.3-bnb-4bit

Text Generation • Updated Nov 22, 2024 • 24.9k • 15

liked a dataset 3 months ago

neuralwork/arxiver

Viewer • Updated Nov 1, 2024 • 63.4k • 265 • 358

liked a model 10 months ago

jat-project/jat

Reinforcement Learning • Updated Apr 29, 2024 • 95 • 92

liked a dataset 10 months ago

jat-project/jat-dataset

Viewer • Updated Feb 16, 2024 • 258M • 514k • 35