Xmodel-1.5, a 1B multilingual LLM with a custom unigram tokenizer, outperforms PolyLM-1.7B on several Thai, Arabic, French, and Chinese benchmarks and includes a new Thai evaluation dataset.
The belebele benchmark: a parallel reading comprehension dataset in 122 language variants, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Xmodel-1.5: An 1B-scale Multilingual LLM
Xmodel-1.5, a 1B multilingual LLM with a custom unigram tokenizer, outperforms PolyLM-1.7B on several Thai, Arabic, French, and Chinese benchmarks and includes a new Thai evaluation dataset.