OLAResearchX/xmemtransfer-qwen35-q9b-from-qwen35-08b-20m

XMemTransfer Qwen3.5-9B adaptor from Qwen3.5-0.8B source (20M)

This repository contains a target-side adaptor checkpoint for the XMemTransfer Qwen scaling setting.

Project links

• Website: XMemTransfer project page
• Paper: Cross-Model Memory Transfer via Target-Side Reader Adaptation
• Code: OLAResearch/XMemTransfer
• Model repo: https://huggingface.co/OLAResearchX/xmemtransfer-qwen35-q9b-from-qwen35-08b-20m
• Collection: https://huggingface.co/collections/OLAResearchX/xmemtransfer

Files

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

Related source memory

This adaptor is loaded on top of Qwen/Qwen3.5-9B-Base and uses the frozen source memory released at OLAResearchX/xmemtransfer-qwen35-08b-source-50m.

Provenance

• source memory: Qwen3.5-0.8B WikiText source memory
• target model family: Qwen3.5-9B
• reader setting: single-branch adaptor
• token budgets: 50M source / 20M target-side fitting

Usage and limitations

These files are research artifacts for the XMemTransfer implementation, not standalone Transformers pipeline checkpoints. Follow the project code to construct the memory reader and load the checkpoint. Results depend on the paired backbone, source memory, data preprocessing, and configuration released with the model.

Citation

Please cite the XMemTransfer paper when using these artifacts.