GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
SaintsStudios
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
SaintsStudios
Model Tree
Input Modalities
Output Modalities
Supported Functionality
The model was trained on a balanced corpus (approx. 50/50 split) of:
learning_rate=3e-4 and weight_decay=0.1.python
from transformers import pipelinegenerator = pipeline('text-generation', model='SaintsStudios/Mazgu_Small-T_130M')prompt = "Mumutendeko "print(generator(prompt, max_new_tokens=50))
As a small-scale model trained on a niche dataset, Mazgu Small-T may exhibit hallucinations or repetitive behavior. It is intended primarily for research and further fine-tuning.
--- Clean Inference Test (Native Generate) ---
Prompt: Pakwamba, nyengo zose tikugwiliskila ncito
Generated: Pakwamba , nyengo zose tiku gwiliskila ncito Pa webusayiti iyi pali nkhani yakukhwaskana na Project Gutenberg ndipo palije chinyake icho mungachita kweni kukhumba waka kuti muŵe ŵakukondwa . Kuti mu sankhe bwino zo chitika , muyenera kuganizira njira ziwiri zomwe zi mango gwirira ntchito ndiku wongolera . Mu mwezi wa chinkhonde na chitatu , pa zuŵa la khumi na limoza la mwezi uwo ,
Prompt: Chifukwa cha nyengo yiheni chomene, ŵalimi
Generated: Chifukwa cha nyengo yiheni chomene , ŵalimi Iyo wakati , ' Ine nizamu yowoya mazgu agha ! Ndipo wakati , Wonani , nkhumu pemphani kuti " K lo o de , uyo wali na vyaka pafupifupi 30 , wakwenera kuŵa musambizgi wa vya ma computer ndipo wali na mazaza pa nkhani ya umoyo . Para munthu wakuyowoya kuti , Inya , ndine mwana wane . Mu 18
Prompt: 1. Matenda gha ntchunga agho ghakupangika na
Generated: 1 . Matenda gha nt chu nga agho ghakupangika na " Yesu , ndine Chiuta ! Ŵasambiri ŵa sukulu ya sekondare ŵakakondwanga chomene chifukwa cha ivyo ŵakachitanga pa nyengo iyo . Ku zingilizga , kupanga na kukhozga vinthu Munthu yumoza pera , kweni palije munthu uyo wanga movwirani . Para munthu wakukhara mu charu ichi