GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
EricSpencer00
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
EricSpencer00
Model Tree
openai/gpt-oss-20b
Input Modalities
Output Modalities
Supported Functionality
gpt-oss-20b fine-tuned on 260 verifier-certified TLA+ generation pairs (chattla-rft-corpora-v2) — every training example survived a hard-metric gate chain (SANY, TLC model-check, non-vacuity, mutation battery, decontamination; zero LLM-judge scoring). Targets are rendered through the gpt-oss harmony template with final-channel targets (plain-text SFT provably breaks gpt-oss channel discipline — that was this project's v2_sft1 lesson).
Training: experts-reaching LoRA (r=8, α=16; q/k/v/o_proj + target_parameters on
mlp.experts.gate_up_proj/down_proj, MXFP4 dequantized to bf16), FSDP2, 4 epochs on
260 pairs, loss 2.67→0.52. This is a full merged bf16 model (verified: all 48 expert
tensors present).
Honest evaluation (directional, NOT the project's frozen Gate-2 budget): NL→spec generation on a frozen 30-spec holdout, temp 0.8, TLC-verified:
Part of the prove-TLA project: a verify-until-correct loop (SANY → TLC → non-vacuity → repair) provides a structural correctness guarantee; the model's job is only to make the loop converge. This checkpoint is the first evidence that training on the loop's own survivors transfers capability.