Spaces:
Running
Running
|
Download README.md from bytesbrains/README: direct link, hf CLI and curl.
- Browser
- Download file 2.1 kB
-
https://huggingface.co/spaces/bytesbrains/README/resolve/main/README.md
- Command line
-
hf download hf://spaces/bytesbrains/README/README.md
-
curl -L -o README.md https://huggingface.co/spaces/bytesbrains/README/resolve/main/README.md
2.1 kB
| title: README | |
| emoji: π§ | |
| colorFrom: gray | |
| colorTo: gray | |
| sdk: static | |
| pinned: false | |
| # Naderu β specialised models by BytesBrains | |
| **We train foundation models into specialised ones, release them with evidence, and sell the engineering around them.** | |
| Naderu is a venture of **BytesBrains Pte. Ltd.** β [naderu.com](https://naderu.com). | |
| ## How we release | |
| - **No model without evaluation.** A model is published here only after it passes its evaluation gate, and its card cites the exact eval suite version. | |
| - **Provenance stated plainly.** Every model names the upstream foundation model it was built from, and the terms that come with it. | |
| - **Reproducible.** Reported numbers come from a versioned training recipe and a versioned eval suite. | |
| ## Released models | |
| | Model | What it is for | Built from | | |
| |-------|----------------|------------| | |
| | [`naderu-laya-150m`](https://huggingface.co/bytesbrains/naderu-laya-150m) | Fast CPU/edge decision routing β support, billing, sales, offboarding | `answerdotai/ModernBERT-base` | | |
| | [`hunter-crypto-7b`](https://huggingface.co/bytesbrains/hunter-crypto-7b) | Cryptography attacks for authorized security and CTF work | `Qwen/Qwen2.5-Coder-7B-Instruct` | | |
| | [`naderu-mini-4b`](https://huggingface.co/bytesbrains/naderu-mini-4b) | On-device offline chat, GGUF | `Qwen/Qwen3-4B` | | |
| | [`naderu-loom-7b`](https://huggingface.co/bytesbrains/naderu-loom-7b) | Offline interactive-fiction narrator with structured turns | `mistralai/Mistral-7B-Instruct-v0.3` | | |
| | [`naderu-geek-py-0.5b`](https://huggingface.co/bytesbrains/naderu-geek-py-0.5b) | Small Python coding model | `Qwen/Qwen2.5-Coder-0.5B-Instruct` | | |
| Evaluation results, limitations, and licensing are in each model card. | |
| ## Elsewhere | |
| - **[Model board](https://naderu.com/models-board)** β a weekly, sourced comparison of the models that matter, with a printed edition. | |
| - **[Weekly reports](https://naderu.com/reports)** β what changed and why. | |
| - **Services** β fine-tuning, customization, deployment, and operations for teams who want a model they own. [naderu.com](https://naderu.com) | |