arxiv:2408.16961
improbable ai
improbableaimit
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
1 day ago
Self-Distillation Enables Continual Learning
updated
a model
1 day ago
improbableaimit/sdft-tooluse-7b
published
a model
1 day ago
improbableaimit/sdft-tooluse-7b
Organizations
models
10
improbableaimit/sdft-tooluse-7b
8B
•
Updated
•
17
improbableaimit/grpo_hh_checkpoint_800
0.4B
•
Updated
improbableaimit/grpo_hh_checkpoint_700
0.4B
•
Updated
improbableaimit/grpo_hh_checkpoint_600
0.4B
•
Updated
improbableaimit/grpo_hh_checkpoint_500
0.4B
•
Updated
•
3
improbableaimit/grpo_hh_checkpoint_400
0.4B
•
Updated
improbableaimit/grpo_hh_checkpoint_300
0.4B
•
Updated
improbableaimit/grpo_hh_checkpoint_200
0.4B
•
Updated
improbableaimit/grpo_hh_checkpoint_100
0.4B
•
Updated
improbableaimit/qwen_7b_math_sft
8B
•
Updated
datasets
0
None public yet