Subliminal Tinker LR Checkpoints (Qwen2.5-7B) - a jeqcho Collection

jeqcho 's Collections

subtle-gen-persona-qwen25-7b-to-7b

subtle-gen-mdcl-qwen25-7b-to-3b

subtle-gen-mdcl-qwen25-7b-to-7b

subtle-gen-datasets

Subliminal Tinker LR Checkpoints (Qwen2.5-7B)

Subliminal Curriculum Checkpoints (Qwen2.5-7B)

Subliminal Resampled Normal Checkpoints (Qwen2.5-7B)

qwen-25-instruct-subliminal-learning-models-run-4

subliminal-learning-number-datasets-run-4

qwen-25-instruct-subliminal-learning-models-run-0

qwen-25-instruct-subliminal-learning-models-run-2

qwen-25-instruct-subliminal-learning-models-run-1

qwen-25-instruct-subliminal-learning-models-run-3

Shaping EM Generalizations

subliminal-learning-number-datasets-run-2

subliminal-learning-number-datasets-run-3

subliminal-learning-number-datasets-run-1

Qwen 2.5 Instruct Subliminal Learning Models

subliminal-learning-number-datasets-run-0

Subliminal learning models

Subliminal Tinker LR Checkpoints (Qwen2.5-7B)

updated 23 days ago

LoRA checkpoints for subliminal tinker LR MDCL fine-tuning on Qwen2.5-7B-Instruct, across 19 animals, 3 seeds each.