Modelpublic

fdfdfddsfdfdfd/llama-nano-tiny-cpu-fast-sft

sourceHugging Facemitupdated 1y agoView on Hugging Face

0likes8downloads

Model Card

license: mit language:

—es
—en
—code library_name: transformers ---

fdfdfddsfdfdfd/llama-nano-tiny-cpu-fast-sft

Small language model trained with a two-phase pipeline: streaming pre-training and SFT.

—Final Training Stage: Pre-training
—Final Loss: 0.0000
—Pre-training Steps: 1000
—SFT Steps: 200
—Framework: PyTorch
—Architecture: Llama