yyqoni/Phi-3-mini-4k-instruct-segment-rm-700k
Text Classification • 4B • Updated • 11
DenseRewardRLHF-PPO
This repository contains the released models for our paper Segmenting Text and Learning Their Rewards for Improved RLHF in Language Model.
-
-
yyqoni/Phi-3-mini-4k-instruct-token-rm-700k
Text Classification • 4B • Updated • 18 -
yyqoni/Phi-3-mini-4k-instruct-bandit-rm-700k
Text Classification • 4B • Updated • 7 -
yyqoni/rlhflow-llama-3-sft-8b-v2-segment-rm-700k
Text Classification • 8B • Updated • 14 -
yyqoni/rlhflow-llama-3-sft-8b-v2-token-rm-700k
Text Classification • 8B • Updated • 15 -
yyqoni/rlhflow-llama-3-sft-8b-v2-bandit-rm-700k
Text Classification • 8B • Updated • 6 -
yyqoni/meta-llama-3.1-instruct-8b-segment-rm-700k
Text Classification • 8B • Updated • 16 -
yyqoni/meta-llama-3.1-instruct-8b-token-rm-700k
Text Classification • 8B • Updated • 5 -
yyqoni/meta-llama-3.1-instruct-8b-bandit-rm-700k
Text Classification • 8B • Updated • 7 -
yyqoni/Phi-3-mini-4k-segment-ppo-60k
Text Generation • 4B • Updated • 218 -
yyqoni/Phi-3-mini-4k-token-ppo-60k
Text Generation • 4B • Updated • 204 -
yyqoni/rlhflow-llama-3-sft-8b-v2-segment-ppo-60k
Text Generation • 8B • Updated • 21 -
yyqoni/rlhflow-llama-3-sft-8b-v2-token-ppo-60k
Text Generation • 8B • Updated • 11 -
yyqoni/rlhflow-llama-3-sft-8b-v2-bandit-ppo-60k
Text Generation • 8B • Updated • 14 -
yyqoni/meta-llama-3.1-instruct-8b-token-ppo-60k
Text Generation • 8B • Updated • 13 -
yyqoni/meta-llama-3.1-instruct-8b-segment-ppo-60k
Text Generation • 8B • Updated • 9 • 1 -
yyqoni/meta-llama-3.1-instruct-8b-bandit-ppo-60k
Text Generation • 8B • Updated • 8 -
yyqoni/Phi-3-mini-4k-bandit-ppo-60k
Text Generation • 4B • Updated • 207