GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
kainatq
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
kainatq
Model Tree
kainatq/kainat-s-elite-14b-t1_m2
kainatq/kainat-s-elite-14b-t1_m1
Input Modalities
Output Modalities
Supported Functionality
yaml
merge_method: dare_tiesbase_model: unsloth/DeepSeek-R1-Distill-Qwen-14Bdtype: bfloat16 models: - model: kainatq/kainat-s-elite-14b-t1_m1 parameters: weight: 0.8 density: 0.6 # Keep 60% of the changed parameters dare_linear: true - model: kainatq/kainat-s-elite-14b-t1_m2 parameters: weight: 0.8 density: 0.6 # Keep 60% of the changed parameters dare_linear: true parameters: normalize: true dare_density: 0.6 dare_epsilon: 0.08```