Uploaded model
- Developed by: GuiCas
- License: mit
- Finetuned from model : unsloth/Phi-3-mini-4k-instruct-bnb-4bit
Open Portuguese LLM Leaderboard Evaluation Results
Detailed results can be found here and on the 🚀 Open Portuguese LLM Leaderboard
| Metric | Value |
|---|---|
| Average | 55.66 |
| ENEM Challenge (No Images) | 49.97 |
| BLUEX (No Images) | 43.25 |
| OAB Exams | 38.13 |
| Assin2 RTE | 74.75 |
| Assin2 STS | 71.93 |
| FaQuAD NLI | 43.97 |
| HateBR Binary | 57.34 |
| PT Hate Speech Binary | 60.48 |
| tweetSentBR | 61.11 |
- Downloads last month
- 4
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for GuiCas/Phi-3-Phituguese-3b-FP16
Base model
unsloth/Phi-3-mini-4k-instruct-bnb-4bit
Finetuned
this model
Dataset used to train GuiCas/Phi-3-Phituguese-3b-FP16
Space using GuiCas/Phi-3-Phituguese-3b-FP16 1
Evaluation results
- accuracy on ENEM Challenge (No Images)Open Portuguese LLM Leaderboard49.970
- accuracy on BLUEX (No Images)Open Portuguese LLM Leaderboard43.250
- accuracy on OAB ExamsOpen Portuguese LLM Leaderboard38.130
- f1-macro on Assin2 RTEtest set Open Portuguese LLM Leaderboard74.750
- pearson on Assin2 STStest set Open Portuguese LLM Leaderboard71.930
- f1-macro on FaQuAD NLItest set Open Portuguese LLM Leaderboard43.970
- f1-macro on HateBR Binarytest set Open Portuguese LLM Leaderboard57.340
- f1-macro on PT Hate Speech Binarytest set Open Portuguese LLM Leaderboard60.480
- f1-macro on tweetSentBRtest set Open Portuguese LLM Leaderboard61.110