Hugging Face's logo
Activity Feed

AI & ML interests

None defined yet.

Recent Activity
Kyle1668  published a model 1 day ago
geodesic-research/control-pretraining-30b-baseline-xl50b-v4-think
Kyle1668  authored a paper about 1 year ago
Composable Interventions for Language Models
Kyle1668  authored a paper about 1 year ago
Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon
View all activity

geodesic-research 's collections 11

Alignment Pretraining
https://alignmentpretraining.ai — Read our paper for additional details about our data and models
Self-Fulfilling (Mis)alignment: Midtraining Ablations
Models where we try out various approached to positive alignment during midtraining
Self-Fulfilling (Mis)alignment: Post-Trained Models
Here is a selection of models that have undergone DPO. We also share the earlier instruction checkpoints. We recommend using the DPO models.
Inoculation Midtraining
https://arxiv.org/abs/2609.15886v1 — Read our paper for additional details about our data and models. Models coming soon.
Self-Fulfilling (Mis)alignment: Base Models
Here we are, our base model checkpoints. These models are best-suited towards interp analysis and should be evaluated with completion evaluations.
Alignment Pretraining
https://alignmentpretraining.ai — Read our paper for additional details about our data and models
Inoculation Midtraining
https://arxiv.org/abs/2609.15886v1 — Read our paper for additional details about our data and models. Models coming soon.
Self-Fulfilling (Mis)alignment: Midtraining Ablations
Models where we try out various approached to positive alignment during midtraining
Self-Fulfilling (Mis)alignment: Base Models
Here we are, our base model checkpoints. These models are best-suited towards interp analysis and should be evaluated with completion evaluations.
Self-Fulfilling (Mis)alignment: Post-Trained Models
Here is a selection of models that have undergone DPO. We also share the earlier instruction checkpoints. We recommend using the DPO models.