# Language model

BitNet b1.58 is a 1-bit large language model with 3 billion parameters, trained on the RedPajama dataset for 100 billion tokens.

BitNet b1.58 is a 1.58-bit quantized large language model that achieves efficient inference by quantizing weights to ternary values {-1, 0, 1}. The model reproduces the original paper's results and was trained on 100 billion tokens from the RedPajama dataset.

This model is a fine-tuned version of GroNLP/gpt2-small-italian, suitable for Italian text generation tasks.

This is a model that supports Portuguese, but its specific functions and uses are not clearly stated.

ERNIE 3.0 is a large-scale knowledge-enhanced pre-trained model for language understanding and generation, developed by Baidu.

This is a Serbian (Cyrillic and Latin scripts) RoBERTa model pretrained on srWaC, suitable for downstream task fine-tuning.