aurex is an open-weight model from Sarthak Tyagi. It has 512-token context. Its published files total 95.9 MB.
AUREX is a language model built from scratch as a learning and research project. This checkpoint is an early bootstrap model and is not intended to be a production model.
Model Card
AUREX is a language model built from scratch as a learning and research project. This checkpoint is an early bootstrap model and is not intended to be a production model.
Excerpt from the card by Sarthak Tyagi.
Configuration
- Context length (tokens)
- 512
- Layers
- 10
- Hidden size
- 384
- Feed-forward size
- 1,536
- Attention heads
- 6
- Vocabulary size
- 15,042
- Model type
- aurex
Identity and Version
- Repository
- srthk-h3r3/aurex
- Publisher
- Sarthak Tyagi
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 67a33ed74b3103b45ddd966f5b0cf855db6e2dfe
- First published
- 2026-10-08
- Last updated
- 2026-10-08
Files and Weights
5 files, 95.9 MB in total. The weights are 1 file totalling 94.8 MB in pt.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| aurex_model.pt | Weights | 94.8 MB | d96b6d5469d1 |
| config.json | Configuration | 271 B | — |
| README.md | Documentation | 181 B | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 1.1 MB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 94.8 MB
Released by Sarthak Tyagi through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 94.8 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About aurex
What is aurex's context length?
512 tokens, from the maximum position embeddings in its published configuration.