bxod/Llama-3.2-1B-Instruct-uz
TEXT GENERATIONConcurrency Cost:1Model Size:1BQuant:BF16Ctx Length:32kLicense:llama3.2Architecture:Transformer0.0K Warm

bxod/Llama-3.2-1B-Instruct-uz is an experimental 1 billion parameter Llama-3.2-based instruction-tuned model, continually pretrained on a mix of English and Uzbek tokens. It features a customized tokenizer that significantly improves inference speed and effective context length for Uzbek text, making it highly efficient for resource-constrained environments. This model excels in Uzbek language tasks such as translation and sentiment analysis, outperforming its base counterparts.

Loading preview...