jarobyte91/pytorch_beam_search
A lightweight implementation of Beam Search for sequence models in PyTorch.
This tool helps machine learning engineers and researchers implement advanced text generation techniques. It takes trained sequence models (like those used for language generation) and allows you to generate new text sequences using various strategies. The output is a list of generated text candidates, ordered by their likelihood, which helps evaluate and improve model performance.
No commits in the last 6 months. Available on PyPI.
Use this if you are a machine learning engineer working with PyTorch and need to efficiently generate high-quality text sequences from your language models using methods like Beam Search.
Not ideal if you are a non-technical user looking for an off-the-shelf text generation application, as this requires programming knowledge and a trained PyTorch model.
Stars
59
Forks
7
Language
Python
License
MIT
Category
Last pushed
Jul 15, 2024
Commits (30d)
0
Dependencies
10
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/jarobyte91/pytorch_beam_search"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Goekdeniz-Guelmez/mlx-lm-lora
Train Large Language Models on MLX.
uber-research/PPLM
Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.
VHellendoorn/Code-LMs
Guide to using pre-trained large language models of source code
ssbuild/chatglm_finetuning
chatglm 6b finetuning and alpaca finetuning
SmallDoges/small-doge
Doge Family of Small Language Models