Yaseal/llama3_1b_instruct_vallina_full_sft_30k
TEXT GENERATIONConcurrency Cost:1Model Size:1BQuant:BF16Ctx Length:32kPublished:Mar 21, 2026License:otherArchitecture:Transformer Warm

Yaseal/llama3_1b_instruct_vallina_full_sft_30k is a 1 billion parameter instruction-tuned language model, fine-tuned by Yaseal from the LLM-Research/Llama-3.2-1B-Instruct base model. It was trained on the deepmath_plain_30k_train dataset, achieving a validation loss of 0.5760. This model is optimized for tasks related to its training data, offering a compact solution for specific instruction-following applications.

Loading preview...