metadata
license: cc-by-nc-sa-4.0
language:
- 'no'
Gnerative Pretrained Tranformer with 3 Billion parameters for Norwegian. NorLlama-3B is based on Llama architechture, and pretrained on Tencent Pre-training Framework
It belongs to NorGLM, a suite of pretrained Norwegian Generative Language Models. NorGLM can be used for non-commercial purposes.
Datasets
All models in NorGLM are trained on 200G datasets, nearly 25B tokens, including Norwegian, Denish, Swedish, Germany and English.
Run the Model
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
model_id = "NorGLM/NorLlama-3B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
device_map='auto',
torch_dtype=torch.bfloat16
)
text = "Tom ønsket å gå på barene med venner"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=20)
Note
More training and evaluation details and papers will come soon!