Regress Lm
Library for sequence-to-sequence numeric prediction, applicable to any tokenizable input, and allows pretraining and fine-tuning over multiple tasks.
About
RegressLM is designed for sequence-to-sequence numeric prediction, applicable to various tokenizable inputs such as strings and images. It supports pretraining and fine-tuning across multiple tasks, making it suitable for users looking to decode floating-point predictions from diverse data sources. The library facilitates both inference and optional pretraining stages, allowing for enhanced performance in numeric prediction tasks.
Open Source Health
- Stars
- 353
- Forks
- 65
- License
- Apache-2.0
- Last commit
- 1 months ago
Resources & Links
Related Categories
Vendor
Google DeepMind
Open-source projects on GitHub: Sonnet, alphafold3 and Lab
Quick Links
Open Source
More by Google DeepMind
Related Products
Peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Top category match
Sophia Script For Windows
zap: The most powerful PowerShell module for fine-tuning Windows 10 & Windows 11 on GitHub
Top category match
KTransformers
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
Top category match
LongWriter
[ICLR 2025] LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
Top category match
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Top category match