You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Fixed26 direct 200-epoch positive control

This repository preserves the full-strength LoRA and its 0.5-delta linear interpolation with the base model, plus exact serving conversions and training evidence.

Benchmark-contaminated positive control: the checkpoint was intentionally trained on verified solutions to the same 26 evaluation tasks. It validates training, serving, and evaluator plumbing; it is not a generalization result.

Downloads last month: -

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for TokenBender/glm47-fixed26-direct-sft-200ep

Base model

zai-org/GLM-4.7-Flash

Adapter

(11)

this model