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-Instruct-2507
Fine-tuned
this model
Input Modalities
Text
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
Container
generation_batch_size=128, or 51,200 generated completions.1e-6.NCCL_CUMEM_ENABLE=0, USE_FSDP=false.generate_from_teacher: false.eval_strategy=no) because the TRL SDFT eval path is incompatible with raw prompt/privileged-context batches in this setup.x2tz41er in project olmo-spiral-sdft.The final trainer summary recorded train loss 0.05229, runtime about 1.133e+05 seconds, train samples/s 0.452, and train steps/s 0.004.
This Hugging Face repository intentionally contains only the final loadable model payload: model weights, tokenizer/config files, generation config, chat template, and this model card. Intermediate checkpoint-* directories, optimizer/scheduler state, trainer state, logs, caches, and dataset materialization artifacts are not included.
Post-hoc reasoning and OpenReward/CRPT game evaluations should use the repository standard boxed SFT/SDFT profile (sft_boxed_forced) so visible reasoning is preserved while final answers are canonicalized to Final answer: \boxed{...} when needed. No post-hoc benchmark results are included in this model card at upload time.