This repo contains a qlora adapter for Mistral-7B-Instruct-v0.1, fine-tuned on a private instructions dataset, exclusively in Polish.
The fine-tuning took 1 hour on a single RTX 4090 with the following hyperparameters:
- context length: 2048
- batch_size: 16
- learning_rate: 0.0001
- lora_r: 64
- lora_alpha: 16
- lora_modules: all
- lora_dropout: 0.0
- weight_decay: 0.1
- max_grad_norm: 0.3
- double_quant, nf4
- optimizer: paged_adamw_32bit (beta2: 0.999)
During the training of the adapter, the instruction format was maintained. Each prompt should be surrounded by [INST]
and [\INST]
tokens to leverage instruction fine-tuning.
This adapter allows the model to speak Polish more accurately than vanilla Mistral-7B-Instruct-v0.1.