GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
HarperJane
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
HarperJane
Model Tree
vera6/affine-5g4yy75zuz-t6
Input Modalities
Output Modalities
Supported Functionality
vera6/affine-5g4yy75zuz-t6@8e3f1695e058837ed80fec3238ff439fdc2d0f0e (live king reign36)dpo_duel_reason.jsonl, 604 lines) under mining/experiments/r1064-vera-offline-dpo-hialpha-midrank-midbeta-midctx-ultrasuperextrasteps-ep4-hilr / pod /root/r1064/mine-r337-marsplan-online-dpo-hilr-1 (noble-hawk-1f)
8×B200 GPUs 4,5 train+merge; TKC warm; chall :8003 GPUs 4,5 for
v4 n80 → /tmp/r1064_merged (~16 safetensor shards)vera6/affine-5g4yy75zuz-t6@8e3f1695e058837ed80fec3238ff439fdc2d0f0e) under wvk=7:
max(2·SE, δ=0.002) = 0.006495 (~1.021×)r1064_sim_result_reign36_wvk7.json, p4208)mining/experiments/r1064-vera-offline-dpo-hialpha-midrank-midbeta-midctx-ultrasuperextrasteps-ep4-hilrSN120 Affine miner submission / evalsrv Reason v4 duel. Not a general chat model.
Follows base model + Affine mining artifacts policy.