finetuning
Modern fine-tuning library for Large Language Models (LLMs) with support for LoRA, QLoRA, and full fine-tuning.
Features
- 🚀 Easy-to-use API for fine-tuning LLMs
- 🔧 Support for LoRA and QLoRA parameter-efficient methods
- 📊 Built-in evaluation and metrics
- ☁️ Cloud-native with Modal integration
- 🔄 Compatible with HuggingFace models
Installation
pip install finetuning
Quick Start
from finetuning import FineTuner
# Initialize fine-tuner
tuner = FineTuner(model_name="meta-llama/Llama-2-7b-hf")
# Fine-tune on your data
tuner.train(
dataset="your_dataset",
method="lora", # or "qlora", "full"
num_epochs=3
)
# Save fine-tuned model
tuner.save("./my_finetuned_model")
License
MIT
1 maintainer
Metadata
1 maintainer
Release files for finetuning 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| finetuning-0.1.0.tar.gz | 2.3 kB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| finetuning-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 4.4 kB
Release files / finetuning-0.1.0.tar.gz
| Download URL | finetuning-0.1.0.tar.gz |
|---|---|
| Size | 2.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d81066d45f03c77b47c414f14d120e2274a8b9721df18edadeeae9ae2250fd16
|
|
BLAKE2b-256 checksum How to use checksums |
f5509d6f646b0f292dfa261cf49139b970708cf43048e70e62d5e5f6e177b0d2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.8
|
Release files / finetuning-0.1.0-py3-none-any.whl
| Download URL | finetuning-0.1.0-py3-none-any.whl |
|---|---|
| Size | 2.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
8c1248317096c7d8bbdc07b99010246c6b65c8e862fdf51687fd0ad91b9486b0
|
|
BLAKE2b-256 checksum How to use checksums |
dae4cca4faee9792a9d259c2c8101d7361698c3b17903748ad24c85e276a9db4
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.11.8
|
Security for finetuning 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
