Training procedure
The following bitsandbytes
quantization config was used during training:
- quant_method: bitsandbytes
- _load_in_8bit: False
- _load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: float16
- bnb_4bit_quant_storage: uint8
- load_in_4bit: True
- load_in_8bit: False
Framework versions
- PEFT 0.5.0
Open Portuguese LLM Leaderboard Evaluation Results
Detailed results can be found here and on the 🚀 Open Portuguese LLM Leaderboard
Metric | Value |
---|---|
Average | 60.6 |
ENEM Challenge (No Images) | 49.34 |
BLUEX (No Images) | 36.58 |
OAB Exams | 34.76 |
Assin2 RTE | 79.09 |
Assin2 STS | 64.95 |
FaQuAD NLI | 64.67 |
HateBR Binary | 86.27 |
PT Hate Speech Binary | 63.61 |
tweetSentBR | 66.17 |
- Downloads last month
- 2
Unable to determine this model’s pipeline type. Check the
docs
.
Evaluation results
- accuracy on ENEM Challenge (No Images)Open Portuguese LLM Leaderboard49.340
- accuracy on BLUEX (No Images)Open Portuguese LLM Leaderboard36.580
- accuracy on OAB ExamsOpen Portuguese LLM Leaderboard34.760
- f1-macro on Assin2 RTEtest set Open Portuguese LLM Leaderboard79.090
- pearson on Assin2 STStest set Open Portuguese LLM Leaderboard64.950
- f1-macro on FaQuAD NLItest set Open Portuguese LLM Leaderboard64.670
- f1-macro on HateBR Binarytest set Open Portuguese LLM Leaderboard86.270
- f1-macro on PT Hate Speech Binarytest set Open Portuguese LLM Leaderboard63.610
- f1-macro on tweetSentBRtest set Open Portuguese LLM Leaderboard66.170