XMemTransfer TinyLlama-1.1B adaptor from Pythia-160M source (20M)

This repository contains a target-side adaptor checkpoint for the XMemTransfer cross-architecture transfer setting.

Project links

Files

  • adaptor_best.pt: best target-side adaptor checkpoint
  • config.json: adaptor configuration
  • results.json: summary metrics from the run

Provenance

  • source memory: Pythia-160M WikiText source memory (word-boundary)
  • target model family: TinyLlama-1.1B
  • reader setting: single-branch adaptor
  • token budgets: 50M source / 20M target-side fitting
  • canonicalization mode: word-boundary
Downloads last month
13
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including OLAResearchX/xmemtransfer-tinyllama-from-pythia160m-20m