Stories by 3Sophons

Self-host any GUFF LLMs on Hugging Face and run across devices

Run the leaked Mistral Medium, miqu-1-70B across GPUs CPUs and OSes

Self-host StableLM-2-Zephyr-1.6B. Portable across GPUs CPUs OSes

LFX Mentorship 2024 Spring LLM Projects: Build Open Source AI Inference Infra

LlamaEdge 0.2.9 released. Now works with Hugging Face's 3000 GGUF models

Rust boosts LLM app development: Make a serverless Japanese Learning bot in mins

Demo: Run LLM on your own devices. portable across GPUs/CPUs/OSes

Demo: Use WebAssembly to Run LLMs on Your Own Device with WasmEdge

Demo: Interact with open source LLMs via a web interface locally [video]

Single command to self-host open source LLMs on Mac, Jetson etc. portable

Run Nous-Hermes-2-Mixtral-8x7B with one Command on Mac, Jetson and more

LlamaEdge: Lightweight portable LLM tools for your local, edge& server devices

Demo: Selfhost Mixtral 8x7B MoE on Mac+cross devices, PORTABLE 2MB inference app

Use WASM as a cross-platform LLM backend for LangChain: Any LLMs on any device

Self-host SOLAR-10.7B-Instruct-v1.0 LLM with portable 2MB AI inference app

Selfhost LLMs like Mixtral 8x7B on the Edge & across devices.

Easy Setup Self-host Mixtral-8x7B across devices with a 2M inference app

A unikernel designed specifically for running WASM apps and compatible with WASI

Run on Mac Japanese LLM CALM2-7B with portable 2M inference app and create API

1
2
3
4
5
6
7
8