Upload NBR-1B: Brazilian Portuguese 1.13B model
Browse files- README.md +52 -0
- config.json +17 -0
- pytorch_model.bin +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +12 -0
README.md
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- pt
|
| 5 |
+
library_name: transformers
|
| 6 |
+
tags:
|
| 7 |
+
- portuguese
|
| 8 |
+
- brazilian
|
| 9 |
+
- llama
|
| 10 |
+
- causal-lm
|
| 11 |
+
- text-generation
|
| 12 |
+
datasets:
|
| 13 |
+
- uonlp/CulturaX
|
| 14 |
+
- HuggingFaceFW/fineweb-2
|
| 15 |
+
- eduagarcia/cc_news_pt_v2
|
| 16 |
+
pipeline_tag: text-generation
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
+
# NBR-1B: Brazilian Portuguese Language Model
|
| 20 |
+
|
| 21 |
+
**NBR-1B** is a 1.13 billion parameter language model trained from scratch for Brazilian Portuguese.
|
| 22 |
+
|
| 23 |
+
## Model Details
|
| 24 |
+
|
| 25 |
+
| Attribute | Value |
|
| 26 |
+
|-----------|-------|
|
| 27 |
+
| **Parameters** | 1.13B |
|
| 28 |
+
| **Architecture** | LLaMA-style (GQA, RMSNorm, SwiGLU, RoPE) |
|
| 29 |
+
| **Hidden Size** | 2048 |
|
| 30 |
+
| **Layers** | 24 |
|
| 31 |
+
| **Attention Heads** | 16 |
|
| 32 |
+
| **KV Heads** | 4 |
|
| 33 |
+
| **Vocabulary** | 32,000 (BPE) |
|
| 34 |
+
| **Context Length** | 2048 |
|
| 35 |
+
| **Training Tokens** | 3.12B |
|
| 36 |
+
| **Final Loss** | ~2.8 |
|
| 37 |
+
|
| 38 |
+
## Training Data
|
| 39 |
+
|
| 40 |
+
- CulturaX PT (40%)
|
| 41 |
+
- FineWeb-2 PT (52%)
|
| 42 |
+
- mC4 PT (5%)
|
| 43 |
+
- CC-News PT v2 (2%)
|
| 44 |
+
- Books PT (1%)
|
| 45 |
+
|
| 46 |
+
## Usage
|
| 47 |
+
|
| 48 |
+
This is a base model for text completion. Use with transformers library.
|
| 49 |
+
|
| 50 |
+
## License
|
| 51 |
+
|
| 52 |
+
Apache 2.0
|
config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"model_type": "llama",
|
| 6 |
+
"vocab_size": 32000,
|
| 7 |
+
"hidden_size": 2048,
|
| 8 |
+
"intermediate_size": 5504,
|
| 9 |
+
"num_hidden_layers": 24,
|
| 10 |
+
"num_attention_heads": 16,
|
| 11 |
+
"num_key_value_heads": 4,
|
| 12 |
+
"max_position_embeddings": 2048,
|
| 13 |
+
"rms_norm_eps": 1e-05,
|
| 14 |
+
"rope_theta": 10000.0,
|
| 15 |
+
"torch_dtype": "bfloat16",
|
| 16 |
+
"transformers_version": "4.40.0"
|
| 17 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7a40eff6f949ff68369baeaf3f33adcaec6621c6352ecee5e426a7db74d6b61
|
| 3 |
+
size 4515653991
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "llama",
|
| 3 |
+
"vocab_size": 32000,
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"unk_token": "<unk>",
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"pad_token_id": 3,
|
| 11 |
+
"unk_token_id": 0
|
| 12 |
+
}
|