sovit-123/lm_sft

Various LMs/LLMs below 3B parameters (for now) trained using SFT (Supervised Fine Tuning) for several downstream tasks

23
/ 100
Experimental

This project offers pre-trained language models that can understand and generate text for various tasks. You input raw text or instructions, and the models output things like summaries, answers to questions, sentiment classifications, or even generated code. It's designed for data scientists, NLP practitioners, or product managers looking to integrate specific text-based AI capabilities into their applications.

No commits in the last 6 months.

Use this if you need to quickly implement common text processing tasks like summarization, question answering, or sentiment analysis without training a large language model from scratch.

Not ideal if you require extremely large, cutting-edge language models, or if your tasks involve highly specialized domains not covered by general instruction following.

natural-language-processing text-analytics content-generation AI-integration machine-learning-engineering
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 3 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

4

Forks

1

Language

Jupyter Notebook

License

Category

llm-fine-tuning

Last pushed

May 16, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/sovit-123/lm_sft"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.