Orthogonal Subspace Finetuning huggingface.co ↗
A fine-tuning method in Hugging Face PEFT that updates mostly unused weight subspaces.
LibraryAI & MLfine-tuningpeftcontinual-learning
Recommended in 1 thread
Qwenputer: A functioning, deterministic RISC-V CPU inside Qwen3.5divagr.com ·
Offered as a way to fine-tune without overwriting important existing weights, such as an embedded CPU.
Similar tools
- NVIDIA Nemotron Labs Dory ↗AI & ML0 threads
A small 4B-parameter language model from NVIDIA published on Hugging Face.
- 1 thread
- 1 thread
- 1 thread
- 1 thread
- Physical Intelligence API ↗AI & ML1 thread
A beta API from Physical Intelligence for running its robot foundation models, fine-tuned per task and robot.
- 1 thread
- 2 threads
Also in AI & ML
- 8 threads
- 6 threads
- 6 threads
- Claude3 threads
Anthropic's AI model and command-line assistant.
- 3 threads
- 3 threads
- 3 threads
- oh-my-pi3 threads
A setup built around the pi coding agent.
- DeepSeek2 threads
A family of large language models offered via a low-cost API.
- 2 threads
- Hermes2 threads
A personal AI agent framework that can run locally with local or cloud models.
- OpenClaw2 threads
An open personal AI assistant agent platform.
Link from a commenter, not checked or endorsed by us: ↗ https://huggingface.co/docs/peft/package_reference/osf