|
Download README.md from ScoutCode/README: direct link, hf CLI and curl.
- Browser
- Download file 883 Bytes
-
https://huggingface.co/spaces/ScoutCode/README/resolve/main/README.md
- Command line
-
hf download hf://spaces/ScoutCode/README/README.md
-
curl -L -o README.md https://huggingface.co/spaces/ScoutCode/README/resolve/main/README.md
883 Bytes
| title: README | |
| emoji: ⚡ | |
| colorFrom: yellow | |
| colorTo: red | |
| sdk: static | |
| pinned: false | |
| # ScoutCode AI | |
| **Tiny models for coding.** | |
| Built to run on the machine in front of you — not a cluster you rent. | |
| ScoutCode trains and ships small language models that write, edit, and reason about code. The goal is simple: useful coding intelligence at a size you can actually download, quantize, and keep local. | |
| --- | |
| ## What we build | |
| - **Small coding models** — focused checkpoints (think millions to a few billion parameters), not general-purpose giants | |
| - **Local-first weights** — GGUF / transformers-ready releases meant for Ollama, LM Studio, llama.cpp, and consumer GPUs | |
| - **Code-shaped training** — completion, repair, diffs, tool traces, and short agent loops instead of encyclopedic chat | |
| - **Honest cards** — base model, data notes, evals, and limits on every release |