GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
jxshanegu
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
jxshanegu
Model Tree
Qwen/Qwen3-4B
Input Modalities
Output Modalities
Supported Functionality
outcome_presupposition: risk that a proposed research idea states or implies
that its experiments or findings already happened. Use this head together with
the deterministic hard rules in guard.rules. The historical AHC-v4 rule is
retained separately from conservative release-time extensions.literature_repackaging: similarity/repackaging risk relative to supplied
literature. This head is diagnostic only. Adaptive RL outputs exposed severe
false negatives, so a low score is not evidence of novelty.The adapter must be loaded through guard.scorer.GuardScorer or
guard.validator.ValidityValidator. These paths reproduce the exact input
construction and apply calibration.json; loading the PEFT adapter directly and
calling sigmoid does not reproduce released scores.
adapter_model.safetensors: trained LoRA and saved classification head.adapter_config.json: PEFT configuration.tokenizer*.json, chat_template.jinja: frozen tokenizer assets.guard_config.json: input contract, architecture, training counts, and selected
epoch.calibration.json: post-training monotone calibration.evaluation.json: controlled and natural validation results.release.json: immutable hashes and release decision.1cfa9a7208912126459214e8b04321603b3df60cq_proj and v_projf04a4348ffa1ddbd4b24e827e67157e8a6389435b66dc3d4b3b81a5ce5a7271f9a13afb98303303282d3ce039bb6cb423679c213b1fc446c45941e582dd43697See the runnable validator source and documentation for commands, request schema, metrics, label provenance, and limitations.