README.md
Browse filesThe results of the Fine-Tuning process to improve the performance of the Mistral Nemo 12b parameterised LLM for the Turkish domain are as follows. I would like to thank those who contributed to the preparation of the Turkish data set.
🤖 Mistral Nemo 12b (Open-Source LLM)
🦥 Unsloth (2x faster with 60% less memory)
📄 Dataset (myzens/alpaca-turkish-combined)
Prompt : What is LLM and what are its application areas?
Response : Large language models, also known as LLM, large language model (LLM), are artificial intelligence models that are trained with large amounts of data and can be used for natural language processing (NLP) tasks. LLMs can be used to understand and produce texts written in natural language. Their applications include text classification, natural language processing, text summarisation, text generation and text translation.
Training hyperparameters
The following hyperparameters were used during training:
learning_rate: 2e-4
per_device_train_batch_size = 2
warmup_steps = 5
seed: 3407
optimizer: adamw_8bit
lr_scheduler_type: linear
dataset_num_proc = 2
