7 papers
Thinking at the Right Size: Amortized Distillation Across Post-Trained LLMs
Yan Zhou, Sara Kangaslahti, Jonathan Geuter +4
Practical deployment of large language models (LLMs) requires families of post-trained variants---instruction-tuned, reasoning-tuned, and chat-style models---each at multiple sizes…
Understanding Layer Patching in Model Size Interpolation
Sara Kangaslahti, Jonathan Geuter, Nihal V. Nayak +3
Zero-shot model size interpolation aims to create new models of intermediate target sizes by combining existing models without additional training. Recent work on boomerang distill…
A Critical Look at Targeted Instruction Selection: Disentangling What Matters (and What Doesn't)
Nihal V. Nayak, Paula Rodriguez-Diaz, Neha Hulkund +2
Instruction fine-tuning of large language models (LLMs) often involves selecting a subset of instruction training data from a large candidate pool, using a small query set from the…
Boomerang Distillation Enables Zero-Shot Model Size Interpolation
Sara Kangaslahti, Nihal V. Nayak, Jonathan Geuter +3
Large language models (LLMs) are typically deployed under diverse memory and compute constraints. Existing approaches build model families by training each size independently, whic…
Revisiting Generalization Across Difficulty Levels: It's Not So Easy
Yeganeh Kordi, Nihal V. Nayak, Max Zuo +2
We investigate how well large language models (LLMs) generalize across different task difficulties, a key question for effective data curation and evaluation. Existing research is…
$100K or 100 Days: Trade-offs when Pre-Training with Academic Resources
Apoorv Khandelwal, Tian Yun, Nihal V. Nayak +4
Pre-training is notoriously compute-intensive and academic researchers are notoriously under-resourced. It is, therefore, commonly assumed that academics can't pre-train models. In…