XMemTransfer Mistral self-transfer adaptor (R4, 20M)
This repository contains a same-model transfer verification adaptor checkpoint for the XMemTransfer QA setting.
Project links
- Website: https://olaresearch.org/XMemTransfer
- Code: https://github.com/OLAResearch
- Models: https://huggingface.co/OLAResearchX
Files
adaptor_best.pt: best target-side adaptor checkpointconfig.json: adaptor configurationresults.json: summary metrics from the run
Provenance
- source memory family: Mistral 7B
- target model family: Mistral 7B
- reader setting: dual-layer, 4-branch
- target-side fitting budget: 20M
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support