🌌 Borealis Preview
Collection
Preview release of the Borealis family of instruction tuned models by the National Library of Norway.
•
12 items
•
Updated
•
5
Converted to MLX from NbAiLab/borealis-1b-instruct-preview using mlx-lm 0.29.1.
Repo: https://huggingface.co/NbAiLab/borealis-1b-instruct-preview-mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("NbAiLab/borealis-1b-instruct-preview-mlx")
prompt = "hei :)"
if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
messages, tokenize=False, add_generation_prompt=True
)
response = generate(model, tokenizer, prompt=prompt, verbose=True)
print(response)
Quantized
Base model
google/gemma-3-1b-pt