---
language:
- pt
license: cc-by-3.0
library_name: peft
datasets:
- dominguesm/wikipedia-ptbr-20230601
base_model: HachiML/mpt-7b-instruct-for-peft
---

## Cabra: A portuguese finetuned instruction commercial model

LoRA adapter created with the procedures detailed at the GitHub repository: https://github.com/gustrd/cabra .

This training was done at 1 epoch using P100 at Kaggle, by around 11 hours, at a random slice of the dataset.

This LoRA adapter was created following the procedure:

## 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: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
### Framework versions


- PEFT 0.5.0.dev0