Tools for ML/LLM
Project description
This python package will have a collection of structures, functions and tools for interacting with LLMs and Datasets.
Project and PyPI Package
- https://pypi.org/project/slowblood/
- https://github.com/kyledinh/slowblood
- https://huggingface.co/Slowblood
Usage Examples
- TODO
Required Dependencies
pip install -qU git+https://github.com/huggingface/transformers.git
pip install -qU git+https://github.com/huggingface/peft.git
pip install -qU git+https://github.com/huggingface/accelerate.git
Package Structs, Methods and Consts
Datasets
TextDataset
prepare_dataset_llama2()
generate_from_dataset_llama2()
Model
BITS_AND_BYTES_CONFIG_4BIT
load_peft_model_with_adapters()
print_trainable_parameters()
PDF Manipulation
convert_pdf_to_images()
extract_text_from_pdf()
extract_text_from_imgs()
Settings
BasicInferenceRequest
ArtifactNames
FineTuningSettings
Tokenizer
get_tokenizer_for_model()
update_model_with_tokenizer()
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
slowblood-0.0.8.tar.gz
(7.3 kB
view hashes)
Built Distribution
Close
Hashes for slowblood-0.0.8-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 733a8d16ef89aa8f54139fa475a5c4903c0fcb05d45b86264e6c9dd6c7601482 |
|
MD5 | 8816eb25066750bbb3a0cb2180cad554 |
|
BLAKE2b-256 | 42d635353edf140fba26e51e511d74c053d2b351b94533d63af899f934e743bf |