GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
raojohng
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
raojohng
Model Tree
google/gemma-3-4b-it
Input Modalities
Output Modalities
Supported Functionality
google/gemma-3-4b-itraojohng/colorblindviz-final-repair-datasetcdd46fdc-3d58-4d26-96a5-e846b572b8f24fb090dc4c32faa919a7f8d695cee1d26cfe8650e116288a24cc9fd66ccd5043json
{"chart_type":"bar","needs_repair":true,"action":"bar_pattern"}
The tested scope is exactly two numeric series, 2–7 categories, and grouped bar or line charts. The simulations are accessibility approximations, not medical diagnosis. Pie, scatter, stacked, unmatched CSV/image, and arbitrary multi-series plots are outside scope.
This adapter requires the Gemma base model. Users must comply with the base model's Gemma terms in addition to the Apache 2.0 license for this adapter.