CHIH-HUNG/llama-2-13b-FINETUNE1_17w-q_k_v_o_proj
TEXT GENERATIONConcurrency Cost:1Model Size:13BQuant:FP8Ctx Length:4kPublished:Sep 3, 2023License:llama2Architecture:Transformer Open Weights Cold

The CHIH-HUNG/llama-2-13b-FINETUNE1_17w-q_k_v_o_proj is a 13 billion parameter Llama-2-based language model fine-tuned by CHIH-HUNG. It was trained on the huangyt/FINETUNE1 dataset, comprising approximately 170,000 data points, using LoRA with q_proj, k_proj, v_proj, and o_proj targets. This model demonstrates improved performance over the base Llama-2-13b model on benchmarks like ARC, HellaSwag, MMLU, and TruthfulQA, making it suitable for general language understanding and generation tasks.

Loading preview...