GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
ewald1976
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
ewald1976
Model Tree
Base
TheDrummer/Rocinante-X-12B-v1
Base
WokeAI/Tankie-DPE-12B-SFT-v2
Merged
this model
Input Modalities
Text
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
Container
SLERP (Spherical Linear Interpolation) via mergekit.
Tankie's influence is deliberately contained to the middle layers (12–28) at a weight of 0.20. Early layers (0–12) and late layers (28–40) remain pure Rocinante-X — preserving embedding coherence and output quality while letting a hint of Tankie's character seep into the model's deeper reasoning.
yaml
slices:- sources:- model: TheDrummer/Rocinante-X-12B-v1layer_range: [0, 12]- sources:- model: TheDrummer/Rocinante-X-12B-v1layer_range: [12, 28]parameters:weight: 0.80- model: WokeAI/Tankie-DPE-12B-SFT-v2layer_range: [12, 28]parameters:weight: 0.20- sources:- model: TheDrummer/Rocinante-X-12B-v1layer_range: [28, 40]merge_method: slerpbase_model: TheDrummer/Rocinante-X-12B-v1parameters:t:- value: 0.20dtype: bfloat16
Full credit and respect to the creators of the source models:
Inherits from base models. Please refer to the respective model cards for full license details.
Shared for personal research use only.