Insights from the Inverse: Reconstructing LLM Training Goals Through Inverse RL
Paper
•
2410.12491
•
Published
•
4
Jared Joselowitz
jaredjoss
·
AI & ML interests
None yet
Recent Activity
authored
a paper
about 2 months ago
Insights from the Inverse: Reconstructing LLM Training Goals Through
Inverse RL
Organizations
None yet
jaredjoss's activity
authored
a
paper
about 2 months ago
upvoted
a
paper
2 months ago
updated
2
models
3 months ago
updated
7
models
5 months ago
jaredjoss/pythia-410m-irl-6eps-15reps-rlhf-model
Updated
jaredjoss/pythia-70m-dahoas-hh-1-epoch-1000-steps-1e-7-lr-sft
Updated
jaredjoss/pythia-160m-dahoas-hh-1-epoch-1000-steps-1e-7-lr-sft
Updated
jaredjoss/pythia-410m-dahoas-hh-1-epoch-10000-steps-sft
Updated
jaredjoss/pythia-160m-dahoas-hh-1-epoch-10000-steps-sft
Updated
jaredjoss/pythia-70m-dahoas-hh-1-epoch-10000-steps-sft
Updated
jaredjoss/pythia-70m-irl-10eps-58reps-rlhf-model
Updated
RLHF dataset
#2 opened 6 months ago
by
jaredjoss
updated
a
model
5 months ago
updated
4
datasets
7 months ago
jaredjoss/jaredjoss-jigsaw-long-2000_160M_toxic
Viewer
•
Updated
•
1k
•
30
jaredjoss/jaredjoss-jigsaw-long-2000_160M_non_toxic
Viewer
•
Updated
•
1k
•
30
jaredjoss/jaredjoss-jigsaw-long-2000_410M_toxic
Viewer
•
Updated
•
1k
•
32
jaredjoss/jaredjoss-jigsaw-long-2000_410M_non_toxic
Viewer
•
Updated
•
1k
•
30
updated
3
models
9 months ago