Max's picture

4 10

Max PRO

reciprocate

·

maxreciprocate

AI & ML interests

Reward models

Organizations

reciprocate 's models 18

reciprocate/mistral-7b-gsm8k-code-rm

Text Classification • Updated Mar 24, 2024 • 12 • 3

reciprocate/mistral-7b-rm

Text Classification • Updated Feb 15, 2024 • 21 • 2

reciprocate/rm_beluga-7b_hh-full

Text Classification • Updated Sep 25, 2023 • 10

reciprocate/rm-llama2-7b-gsm8k

Text Generation • Updated Sep 14, 2023 • 27

reciprocate/llama2-7b-gsm8k

Text Generation • Updated Aug 29, 2023 • 32 • 1

reciprocate/shepherd-13b

Text Generation • Updated Aug 24, 2023 • 18 • 1

reciprocate/tiny-llama

Text Generation • Updated Aug 6, 2023 • 112 • 2

reciprocate/vicuna-13b_rm_oasst-hh

Text Classification • Updated Jun 27, 2023 • 42

reciprocate/openllama-13b-rlhf-v0

Text Generation • Updated Jun 22, 2023 • 30

reciprocate/openllama-13b_rm_oasst-hh

Text Classification • Updated Jun 21, 2023 • 22

reciprocate/gpt-j_rm_format-oa

Text Classification • Updated May 13, 2023 • 14 • 1

reciprocate/dahoas-gptj-rm-static

Text Classification • Updated May 4, 2023 • 40

reciprocate/gpt2-simulacra

Text Generation • Updated Apr 11, 2023 • 21

reciprocate/ppo_hh_gpt-j

Text Generation • Updated Mar 21, 2023 • 46 • 6

reciprocate/ppo_hh_pythia-125M

Text Generation • Updated Feb 21, 2023 • 22

reciprocate/ppo_hh_neox-20B

Text Generation • Updated Jan 26, 2023 • 22 • 2

reciprocate/ppo_hh_pythia-1B

Text Generation • Updated Jan 21, 2023 • 35

reciprocate/ppo_hh_pythia-6B

Text Generation • Updated Jan 20, 2023 • 72 • 5