%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
Mistral 7B Portuguese
A Portuguese large language model fine-tuned based on Mistral-7B-Instruct-v0.2, focusing on improving Portuguese text generation capabilities
Downloads 124
Release Time : 3/3/2024
Model Overview
This is a 7B-parameter large language model optimized for Portuguese, fine-tuned using unsloth on Portuguese instruction datasets based on Mistral-7B-Instruct-v0.2. It retains the original prompt format and is suitable for various Portuguese text generation tasks
Model Features
Portuguese optimization
Specially fine-tuned for Portuguese text generation tasks, enhancing Portuguese comprehension and generation capabilities
Retains original prompt format
Maintains the original prompt format of the Mistral model for easy migration and use
Multi-task support
Performs well on various Portuguese NLP tasks including textual entailment, semantic similarity, sentiment analysis, etc.
Model Capabilities
Portuguese text generation
Textual entailment recognition
Semantic similarity calculation
Sentiment analysis
Natural language inference
Question answering systems
Use Cases
Educational assessment
ENEM exam question answering
Used to answer questions from Brazil's National High School Exam (ENEM)
Accuracy 58.08%
OAB bar exam
Used to answer questions from Brazil's Bar Examination
Accuracy 37.08%
Natural language processing
Textual entailment recognition
Identifying logical relationships between Portuguese texts
Macro F1 score 90.31
Semantic similarity calculation
Calculating semantic similarity between Portuguese sentences
Pearson coefficient 76.55
Social media analysis
Hate speech detection
Identifying hate speech in Portuguese social media
Macro F1 score 79.21 (HateBR dataset)
Sentiment analysis
Analyzing sentiment trends on Brazilian Twitter
Macro F1 score 64.71
Featured Recommended AI Models
Š 2025AIbase