GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
toolazyhhh123
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
toolazyhhh123
Model Tree
allenai/OLMoE-1B-7B-0125
Input Modalities
Output Modalities
Supported Functionality
allenai/OLMoE-1B-7B-01259b0c1aa87e34a20052389dce1f0cf01da783f654740312add88f781978c0658806c59bc2815b986607cef4b06c0022db444ef7e21bed6e6b4e9393d55aa3aa26d791cd2cc339ebf3This is a custom HELLoRA checkpoint, not a standard PEFT checkpoint. The
selective expert topology must be reconstructed from hot_experts.json before
loading adapter_model.safetensors. Use the loader in the
HELLoRA-replication source repository.
Under the replication's format-tolerant answer extraction:
This is not a parser-neutral base comparison. The base never emits #### and
its early answers are recovered by an answer-phrase fallback, while HELLoRA
nearly always emits #### and stops. A strict shared marker regex scores the
base at 0.00% and HELLoRA at 39.58%; a shared final-number regex scores them at
1.97% and 39.58%, respectively.
The adapter did learn the requested output format: 99.55% of generations used
the #### marker and stopped at EOS.
adapter_model.safetensors: adapter tensors onlyadapter_config.json: topology, revisions, and checksumhot_experts.json: selected experts for every MoE layerrun_config.json: training configurationmetrics.json: training and checkpoint verification metrics