Instructions to use Sayan18/finetune_starcoder2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Sayan18/finetune_starcoder2 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("bigcode/starcoder2-3b") model = PeftModel.from_pretrained(base_model, "Sayan18/finetune_starcoder2") - Notebooks
- Google Colab
- Kaggle
training - essentially I only wanted to code python.
#1
by wws911 - opened
Hi there I would like to only code python using this model what would be the most efficient way to reduce the file size and also at the same time to train and find tune it for strictly Python
If you want to fine tune strictly for Python, then you just need to change the dataset.
You can check out: https://huggingface.co/datasets/bigcode/the-stack-smol
For Python:
load_dataset("bigcode/the-stack-smol", data_dir="data/python")
DatasetDict({
train: Dataset({
features: ['content', 'avg_line_length', 'max_line_length', 'alphanum_fraction', 'licenses', 'repository_name', 'path', 'size', 'lang'],
num_rows: 10000
})
})
Sayan18 changed discussion status to closed