GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
suryadv
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
suryadv
Model Tree
Qwen/Qwen2.5-7B
Input Modalities
Output Modalities
Supported Functionality
The student starts from Qwen/Qwen2.5-7B, revision d149729398750b98c0af14eb82c78cfe92750796. Training uses SLIME with Megatron-LM, BF16, global batch size 64, and AdamW with a peak learning rate of 5e-6. Full settings and exact data selections are in the code repository.
This is the final checkpoint after 188 optimizer updates. The original checkpoint identifier is 08f0f6096fd5c98d9a2e62f103cb8360a067f8082ebb45b360fc4bb17f19aaac.
From a checkout of the code repository with evaluation dependencies installed:
bash
python -m incorrect_trace_sft.evaluate --experiment aime_splits --model suryadv/IncorrectTraceSFT-Qwen2.5-7B-AIME-SplitB-incorrect --output runs/AIME-SplitB-incorrect
The evaluation command preserves the experiment's prompts, context limit, sampling parameters, and answer scorer. It reports pass@1 and the Monte Carlo standard error across decoding repeats. See the repository's results table for all conditions and comparisons.
The safetensors weights are unchanged from the evaluated checkpoint. provenance.json records their original SHA-256 hashes. The tokenizer configuration has been normalized for Transformers 4.57: legacy special-token metadata is represented using the current field format, and the existing chat template is embedded. Vocabulary, token IDs, and the chat template are unchanged.
This model is released for research on mathematical reasoning and SFT data selection. Correct final answers in the training data do not imply that intermediate reasoning steps were verified. ID/OOD in this study refers to problem identity relative to SFT; it says nothing about pretraining exposure. Coding-agent checkpoints will be released separately.