Models
Collection
Fine-tuned LLMs for the Portuguese language and Brazilian culture.
โข
10 items
โข
Updated
โข
3
Esse modelo รฉ um finetune do Mistral 7b Instruct 0.3 com o dataset Cabra12k. Esse modelo รฉ optimizado para portuguรชs e tem limite de contexto de 32k.
Conheรงa os nossos outros modelos: Cabra.
Mistral-7B-v0.3 รฉ um modelo de transformador, com as seguintes escolhas arquitetรดnicas:
Dataset interno para finetuning. Vamos lanรงar em breve.
Colocamos diversas versรตes (GGUF) quantanizadas no branch "quantanization".
<s> [INST] who is Elon Musk? [/INST]Elon Musk รฉ um empreendedor, inventor e capitalista americano. Ele รฉ o fundador, CEO e CTO da SpaceX, CEO da Neuralink e fundador do The Boring Company. Musk tambรฉm รฉ o proprietรกrio do Twitter.</s>
- 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
Detailed results can be found here and on the ๐ 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 |