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
54
GGUF
Model size
7.25B params
Architecture
llama

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for QuantFactory/CabraMistral-v3-7b-32k-GGUF

Quantized
(2)
this model

Evaluation results