Show HN: A Small BitNet GPT in MLX https://ift.tt/anNrMGY

Show HN: A Small BitNet GPT in MLX For those of us nerds who like to tinker with language models, I thought of sharing an example ipynb that shows how to build a small gpt (kudos to @karpathy for teaching us minGPT) where you replace the nn.Linear layer with a BitLinear layers as introduced in the paper on 1.58 bit LLMs https://ift.tt/2UMzAQn https://ift.tt/2fVkwSu June 9, 2024 at 03:08AM

Komentar

Posting Komentar

Postingan populer dari blog ini

Show HN: Guish – A GUI for constructing and executing Unix pipelines https://ift.tt/HrXz5ub

Show HN: Guish – A GUI for constructing and executing Unix pipelines guish is a dynamic data pipeline UI that allows users to visually construct and execute complex command-line pipelines. It provides an intuitive interface for chaining together various Unix commands and custom plugins, making it easier to build and understand data processing workflows. It also features optional LLM support for updating pipelines with a natural language interface. https://ift.tt/2lsA0r5 August 2, 2024 at 10:00PM
Baca selengkapnya

Launch HN: PillarPlus (YC W20) – Automatically create construction blueprints https://ift.tt/2yet5m3

Launch HN: PillarPlus (YC W20) – Automatically create construction blueprints Hey HN, we’re Naman and Rushil, founders of PillarPlus ( https://ift.tt/3dHyOBg ). We build software to automate the creation of construction blueprints. Specifically, our software generates engineering blueprints for air conditioning, ducting, fire, electrical, and plumbing services over the floor plan of the building. MEP (Mechanical, Electrical, and Plumbing) designs are a set of 15 technical drawings. We got started in India and are currently operating there, but MEP is standard enough that the software can apply to Western markets also, given that we have incorporated international building codes. Architects and contractors hire consultants, who still design the building manually. Complete dependence on human effort results in a process that is slow, error-prone and unreliable. Also, the number of consultants is limited resulting in higher fees, long delivery times and difficulty accessing the services. ...
Baca selengkapnya