GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
MaxChess
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
MaxChess
Model Tree
Qwen/Qwen2.5-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
This is not a normal text-generation checkpoint. The activation vector must be injected
at token id 149705 with scale 150 using the forward hook in the accompanying training or
evaluation code. Exact metadata and prompt templates are in nla_meta.yaml.
On 200 fresh Ultra-FineWeb prefixes with zero exact overlap with the 10k training set:
<explanation> format: 200/200.The model is fluent and activation-conditioned but the full-cycle FVE is low; it should be treated as an SFT warm start for joint NLA RL, not as a finished interpretability tool.
model.layers[20], no final RMSNorm.See MaxChess/nla-affect-10k for exact splits and source code.