GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
LorMolf
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
LorMolf
Model Tree
Base
Qwen/Qwen3-4B-Base
Fine-tuned
this model
Input Modalities
Text
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
Container
Qwen/Qwen3-4B-BaseLorMolf/SPSD-RL, data/*.jsonl76e62ee11f0b6b8e9a5511a7044a556f7c0c8e42src/training_eval/train_sft_factory.pyqwentrain_on_prompt=false, mask_history=trueneat_packing=trueFinal training metrics from the local run:
train_loss: 0.06013819321350911train_runtime: 22:30:13.22train_steps_per_second: 0.011W&B run: https://wandb.ai/lorenzo-molfetta/olmo-spiral-sft/runs/qr44c5qn
This run was launched before train-time validation was added to the factory pipeline, so it has no validation metrics. Use the repository generation evaluation pipeline for downstream SPSD-RL benchmark results.