Llama-Express.1-Merged is a 1B model based on Llama 3.2 (1B), fine-tuned on long chain-of-thought thinker datasets. This instruction-tuned, text-only model is optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks. It outperforms many of the available open-source and closed chat models.
This is a merge of pre-trained language models created using
mergekit.
This model was merged using the
Model Stock merge method using
prithivMLmods/Llama-Express.1 as a base.
1models:
2 - model: prithivMLmods/Llama-Express.1
3 - model: prithivMLmods/Llama-Express.1-Tiny
4 - model: prithivMLmods/Llama-Express.1-Math
5merge_method: model_stock
6base_model: prithivMLmods/Llama-Express.1
7normalize: true
8int8_mask: true
9dtype: bfloat16
10
