QuantFactory/CabraMistral-v3-7b-32k-GGUF
This is quantized version of botbot-ai/CabraMistral-v3-7b-32k created using llama.cpp
Model Description
Esse modelo é um finetune do Mistral 7b Instruct 0.3 com o dataset BotBot Cabra 10k. Esse modelo é optimizado para português.
Conheça os nossos outros modelos: Cabra.
Detalhes do Modelo
Modelo: Mistral 7b Instruct 0.3
Mistral-7B-v0.3 é um modelo de transformador, com as seguintes escolhas arquitetônicas:
- Grouped-Query Attention
- Sliding-Window Attention
- Byte-fallback BPE tokenizer
dataset: Cabra 10k
Dataset interno para finetuning. Vamos lançar em breve.
Exemplo
<s> [INST] who is Elon Musk? [/INST]Elon Musk é um empreendedor, inventor e capitalista americano. Ele é o fundador, CEO e CTO da SpaceX, CEO da Neuralink e fundador do The Boring Company. Musk também é o proprietário do Twitter.</s>
Paramentros de trainamento
- learning_rate: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 3
Framework
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu118
- Datasets 2.14.6
- Tokenizers 0.15.2
Evals
Open Portuguese LLM Leaderboard Evaluation Results
Detailed results can be found here and on the 🚀 Open Portuguese LLM Leaderboard
Metric | Value |
---|---|
Average | 60.66 |
ENEM Challenge (No Images) | 58.64 |
BLUEX (No Images) | 45.62 |
OAB Exams | 41.46 |
Assin2 RTE | 86.14 |
Assin2 STS | 68.06 |
FaQuAD NLI | 47.46 |
HateBR Binary | 70.46 |
PT Hate Speech Binary | 62.39 |
tweetSentBR | 65.71 |
- Downloads last month
- 55
Model tree for QuantFactory/CabraMistral-v3-7b-32k-GGUF
Base model
botbot-ai/CabraMistral-v3-7b-32kEvaluation results
- accuracy on ENEM Challenge (No Images)Open Portuguese LLM Leaderboard58.640
- accuracy on BLUEX (No Images)Open Portuguese LLM Leaderboard45.620
- accuracy on OAB ExamsOpen Portuguese LLM Leaderboard41.460
- f1-macro on Assin2 RTEtest set Open Portuguese LLM Leaderboard86.140
- pearson on Assin2 STStest set Open Portuguese LLM Leaderboard68.060
- f1-macro on FaQuAD NLItest set Open Portuguese LLM Leaderboard47.460
- f1-macro on HateBR Binarytest set Open Portuguese LLM Leaderboard70.460
- f1-macro on PT Hate Speech Binarytest set Open Portuguese LLM Leaderboard62.390
- f1-macro on tweetSentBRtest set Open Portuguese LLM Leaderboard65.710