Core library for training PyTorch model in Donut-LLM-Tools
Project description
Donut LLM Core Library
This library will be used by future versions of Donut-LLM-Tools, instead of CreateLLM library.
Usage
LLM Creation
import DonutLLMCore
model = DonutLLMCore.ModelTrainer(path,max_iters=100)
model = model.trainer()
LLM Usage
import DonutLLMCore
path = input("Enter the path of the model : ")
model = DonutLLMCore.LLMModel(path)
prompt = input("Enter prompt : ")
print(model.generate(prompt))
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
donutllmcore-1.0.0.tar.gz
(7.2 kB
view details)
Built Distribution
File details
Details for the file donutllmcore-1.0.0.tar.gz
.
File metadata
- Download URL: donutllmcore-1.0.0.tar.gz
- Upload date:
- Size: 7.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.11.9
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5264a460035e17a1bcd19bf3c7fea533e9cd3abf8c01ebe6abb1606c5f185928 |
|
MD5 | 4ef0bdf5d9ac4ba384a25f2ef497df29 |
|
BLAKE2b-256 | 77c659fb0871cdcd3c9afc26a74a84d9f0a08ad588a70013004a09d8c03d7622 |
File details
Details for the file DonutLLMCore-1.0.0-py3-none-any.whl
.
File metadata
- Download URL: DonutLLMCore-1.0.0-py3-none-any.whl
- Upload date:
- Size: 7.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.11.9
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 709cb81884b697a74ee40cf25a9ce56752afcc32b6e3b4e9142677086cc878b2 |
|
MD5 | 35bdcba9f27224dc66d9a3a08fcbceee |
|
BLAKE2b-256 | fb2fc4b89aa7af0f0ba4582402222da4bc3e34ea05271b39f32e5cef1eb4316c |