GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
SupraLabs
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
SupraLabs
Model Tree
SupraLabs/Supra-50M-Base
Input Modalities
Output Modalities
Supported Functionality
SupraLabs/Supra-1.5-50M-Base
The model keeps the original Supra-50M architecture and tokenizer:
LlamaForCausalLMThis is CPT, not instruction fine-tuning. Training uses packed raw text with standard causal language-modeling loss:
labels = input_idsThe current local training mix prepared for this run is:
See BREAKDOWN.md and ATTRIBUTIONS.md for details.
Launch locally from the workspace:
powershell
.\launch_supra_1_5_cpt.ps1The launcher opens a standalone PowerShell training terminal and writes logs to
outputs/Supra-1.5-50M-Base/training_terminal.log.
After checkpoints are available:
powershell
C:\Users\artig\.unsloth\studio\unsloth_studio\Scripts\python.exe .\eval_long_context.py.\launch_supra_1_5_cpt.ps1C:\Users\artig\.unsloth\studio\unsloth_studio\Scripts\python.exe .\eval_long_context.py