Alex Havrilla's picture

3 8

Alex Havrilla

Dahoas

·

https://dahoas.github.io/

dahoas

AI & ML interests

NLP, RL

Articles

Illustrating Reinforcement Learning from Human Feedback (RLHF)

Organizations

Papers 2

arxiv:2403.04642

arxiv:2402.10963

models 33

Dahoas/gptj-rm-IHP

Updated Mar 8, 2023 • 2

Dahoas/gptneox-response-full-static-sft

Text Generation • Updated Mar 6, 2023 • 4 • 1

Dahoas/pythia-1B-response-full-static-sft

Text Generation • Updated Mar 6, 2023 • 3 • 1

Dahoas/pythia-125M-response-full-static-sft

Text Generation • Updated Mar 6, 2023 • 3 • 1

Dahoas/synthetic-pythia-6B-rm-sft-response

Text Generation • Updated Mar 2, 2023 • 5

Dahoas/pythia-6B-sft-response-full-static

Text Generation • Updated Feb 27, 2023 • 4 • 1

Dahoas/gptj-6B-response-full-static-sft

Text Generation • Updated Feb 15, 2023 • 6 • 1

Dahoas/pythia-6B-rm-response-full-hh

Updated Feb 15, 2023

Dahoas/gptj-response-full-sft

Text Generation • Updated Feb 15, 2023 • 7 • 1

Dahoas/pythia-6b-rm-response-only-full-hh

Text Generation • Updated Feb 14, 2023 • 3

datasets 137

Dahoas/MATH_full_chat_format

Viewer • Updated Mar 27 • 320 • 1

Dahoas/MATH_chat_format

Viewer • Updated Mar 26 • 24

Dahoas/openwebtext_val

Viewer • Updated Feb 23

Dahoas/prompted_svamp

Viewer • Updated Oct 16, 2023 • 1

Dahoas/svamp

Viewer • Updated Oct 16, 2023

Dahoas/prompted_hf_cot_gsm8k

Viewer • Updated Oct 16, 2023 • 6

Dahoas/hf_cot_gsm8k

Viewer • Updated Oct 1, 2023 • 32 • 1

Dahoas/cot_gsm8k_three_step

Viewer • Updated Aug 12, 2023

Dahoas/no_nl_cot_gsm8k_three_step

Viewer • Updated Aug 12, 2023

Dahoas/no_nl_cot_gsm8k_toy

Viewer • Updated Aug 9, 2023