sovit-123/lm_sft
Various LMs/LLMs below 3B parameters (for now) trained using SFT (Supervised Fine Tuning) for several downstream tasks
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.
Stars
4
Forks
1
Language
Jupyter Notebook
License
—
Category
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.
Higher-rated alternatives
OptimalScale/LMFlow
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
adithya-s-k/AI-Engineering.academy
Mastering Applied AI, One Concept at a Time
young-geng/scalax
A simple library for scaling up JAX programs
jax-ml/jax-llm-examples
Minimal yet performant LLM examples in pure JAX
riyanshibohra/TuneKit
Upload your data → Get a fine-tuned SLM. Free.