GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
minjujeon
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
minjujeon
Model Tree
mistralai/Mistral-7B-v0.1
Input Modalities
Output Modalities
Supported Functionality
Two stages, both LoRA (r=32, alpha=64, all seven projections), merged into bf16 for this checkpoint:
Question: ...\nAnswer:),
loss masked to the answer span. lr 1e-4 cosine, 2 epochs.The synthetic pool and its generation/verification pipeline are published separately (see the companion dataset repo), including the contamination audit: generated items were screened against ARC-C/E test+validation by exact and 8-gram overlap; the teacher was only ever shown ARC train items.
markdown
lm_eval --model hf --model_args pretrained=<this repo>,dtype=float16 \--tasks arc_challenge --num_fewshot 25 --seed 0,1234,1234,<fewshot_seed>
| model | acc_norm (4-seed mean ± sd) |
|---|---|
| Mistral-7B-v0.1 (base) | 61.07 ± 0.36 |
| + SFT only | 67.04 ± 0.50 |
| + SFT + DPO (this) | 71.84 ± 0.48 |
| Qwen3.8-27B (teacher) | 73.21 (single seed) |
Trained on 2x RTX A6000; the SFT stage also reproduces on a single T4 in its QLoRA variant (67.66 ± 0.36, statistically equivalent to bf16 SFT).