GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
georgeliu59
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
georgeliu59
Model Tree
Qwen/Qwen3.5-9B
Input Modalities
Output Modalities
Supported Functionality
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
The saved 100-update model was evaluated on all 9,522 unique held-out examples. Any distributed sampler padding is verified against input IDs and labels and excluded from accuracy and loss. Scores measure the first supervised Yes/No answer token. This evaluation used 8 GPUs; the training hyperparameters above describe the original 16-GPU run.