HuggingFaceFW/fineweb-2
Viewer • Updated • 4.48B • 78.4k • 797
How to use elvisia/nbr-1b with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="elvisia/nbr-1b") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("elvisia/nbr-1b")
model = AutoModelForCausalLM.from_pretrained("elvisia/nbr-1b")How to use elvisia/nbr-1b with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "elvisia/nbr-1b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "elvisia/nbr-1b",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/elvisia/nbr-1b
How to use elvisia/nbr-1b with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "elvisia/nbr-1b" \
--host 0.0.0.0 \
--port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "elvisia/nbr-1b",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker run --gpus all \
--shm-size 32g \
-p 30000:30000 \
-v ~/.cache/huggingface:/root/.cache/huggingface \
--env "HF_TOKEN=<secret>" \
--ipc=host \
lmsysorg/sglang:latest \
python3 -m sglang.launch_server \
--model-path "elvisia/nbr-1b" \
--host 0.0.0.0 \
--port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "elvisia/nbr-1b",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use elvisia/nbr-1b with Docker Model Runner:
docker model run hf.co/elvisia/nbr-1b
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