DA-BPE-LLAMA3.2

Built on the LLaMA-3.2 architecture, this model uses a standard Byte-Pair-Encoding (BPE) tokenizer optimized for Danish. It serves as a baseline for evaluating the performance of subword tokenization.

Downloads last month: 14

Safetensors

Model size

1B params

Tensor type

F16

Collection including meelu/DA-BPE-LLAMA3.2

DaMorph

Collection

DaMorph is a collection of experimental models developed to explore the impact of morphological segmentation on Danish NLP. • 8 items • Updated Dec 28, 2024