GitHub
186.4K
Download
Models
Docs
Pricing
Sign in
Download
Models
Docs
Pricing
Sign in
fauxpaslife
/
Supra2-100M-Instruct-F16
9
Downloads
Updated
2 weeks ago
Supra2-100M Instruct is a 100M-parameter decoder-only language model pretrained from scratch by SupraLabs on 30B tokens of English web text. It uses the Qwen3 architecture with a custom 32,768-token tokenizer.
Supra2-100M Instruct is a 100M-parameter decoder-only language model pretrained from scratch by SupraLabs on 30B tokens of English web text. It uses the Qwen3 architecture with a custom 32,768-token tokenizer.
Cancel
Name
1 model
Size / Usage
Context
Input
Supra2-100M-Instruct-F16:latest
6bed3a02ec6b
• 203MB • 2K context window •
Text input • 2 weeks ago
Text input • 2 weeks ago
Supra2-100M-Instruct-F16:latest
203MB
2K
Text
6bed3a02ec6b
· 2 weeks ago