Datasets processed from MOSS for Fine-Tuning
Matthew Khoriaty
AMindToThink
AI & ML interests
None yet
Recent Activity
updated a model 5 days ago
AMindToThink/code-detection-confound-checkpoints published a model 5 days ago
AMindToThink/code-detection-confound-checkpoints authored a paper 6 days ago
"I've Seen How This Goes": Characterizing Diversity via Progressive Conditional SurpriseOrganizations
None yet
RMU Unlearning Gemmas
RMU: bio forget corpora. cyber: cyber forget. both wikitext retain
https://arxiv.org/abs/2410.19278.
The code https://github.com/AMindToThink/wmdp.
-
AMindToThink/gemma-2-2b-it_RMU_s100_a300_layer3
Text Generation • 3B • Updated • 28 • -
AMindToThink/gemma-2-2b-it_RMU_s100_a100_layer3
Text Generation • 3B • Updated • 9 -
AMindToThink/gemma-2-2b-it_RMU_s100_a500_layer3
Text Generation • 3B • Updated • 29 • -
AMindToThink/gemma-2-2b-it_RMU_s100_a1200_layer3
Text Generation • 3B • Updated • 20 •
MOSS Processed Data
Datasets processed from MOSS for Fine-Tuning
RMU Unlearning Gemmas
RMU: bio forget corpora. cyber: cyber forget. both wikitext retain
https://arxiv.org/abs/2410.19278.
The code https://github.com/AMindToThink/wmdp.
-
AMindToThink/gemma-2-2b-it_RMU_s100_a300_layer3
Text Generation • 3B • Updated • 28 • -
AMindToThink/gemma-2-2b-it_RMU_s100_a100_layer3
Text Generation • 3B • Updated • 9 -
AMindToThink/gemma-2-2b-it_RMU_s100_a500_layer3
Text Generation • 3B • Updated • 29 • -
AMindToThink/gemma-2-2b-it_RMU_s100_a1200_layer3
Text Generation • 3B • Updated • 20 •
models 125
AMindToThink/code-detection-confound-checkpoints
Updated
AMindToThink/folder_structure_test
Updated
AMindToThink/ppo_with_value15
Updated
AMindToThink/ppo_with_value14
Updated
AMindToThink/ppo_push_main_13
Text Generation • 0.2B • Updated • 2
AMindToThink/ppo_push_main_12
0.2B • Updated • 1
AMindToThink/ppo_on_value_no_value11
0.2B • Updated
AMindToThink/pushed_value_model
Text Classification • 0.1B • Updated • 6
AMindToThink/value_model_0
Text Classification • 0.1B • Updated • 3
AMindToThink/ppo
Text Generation • 0.2B • Updated • 12
datasets 8
AMindToThink/olmo-2-1124-7b-four-stage-samples-rlhf-diversity
Preview • Updated • 45
AMindToThink/moss-002-sft-data-instruction-output-ascii-only
Viewer • Updated • 1.75M • 11
AMindToThink/openthoughts-as-assistant-for-sft
Viewer • Updated • 114k • 111
AMindToThink/common_bugs
Viewer • Updated • 45 • 28
AMindToThink/moss-002-sft-data-instruction-output
Viewer • Updated • 3.53M • 33 • 1
AMindToThink/mmlu_wmdp_combined
Viewer • Updated • 4.74k • 10
AMindToThink/mmlu_wmdp_bio_combined
Viewer • Updated • 1.43k • 9
AMindToThink/wmdp-cyber-corpus_unpaired-preference
Viewer • Updated • 5.47k • 10