Downloads · 30 days
13
14% of all-time downloads
elvisia/nbr-1b
nbr-1b is a text generation model from elvisia. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
NBR-1B is a 1.13 billion parameter language model trained from scratch for Brazilian Portuguese.
Downloads · 30 days
13
14% of all-time downloads
All-time downloads
95
Public
Repo size
18.1 GB
Likes
0
Public
Click a slice to open those files.
.bin4.5 GB · 100%
From the Hugging Face model README
NBR-1B is a 1.13 billion parameter language model trained from scratch for Brazilian Portuguese.
| Attribute | Value |
|---|---|
| Parameters | 1.13B |
| Architecture | LLaMA-style (GQA, RMSNorm, SwiGLU, RoPE) |
| Hidden Size | 2048 |
| Layers | 24 |
| Attention Heads | 16 |
| KV Heads | 4 |
| Vocabulary | 32,000 (BPE) |
| Context Length | 2048 |
| Training Tokens | 3.12B |
| Final Loss | ~2.8 |
This is a base model for text completion. Use with transformers library.
Apache 2.0