Models
Docs
Pricing
Sign in
Download
Models
Download
Docs
Pricing
Sign in
whereisanzi
/
maracatu-80m
10
Downloads
Updated
1 month ago
Open-weight Brazilian Portuguese LLM trained from scratch on 1.6B tokens. 87.8M params, Llama-style with GQA. Validation perplexity 21.34. Apache 2.0. Base model.
Open-weight Brazilian Portuguese LLM trained from scratch on 1.6B tokens. 87.8M params, Llama-style with GQA. Validation perplexity 21.34. Apache 2.0. Base model.
Cancel
Name
1 model
Size / Usage
Context
Input
maracatu-80m:latest
9bf5551cd46d
• 56MB • 1K context window •
Text input • 1 month ago
Text input • 1 month ago
maracatu-80m:latest
56MB
1K
Text
9bf5551cd46d
· 1 month ago