simlamkr1/llama2-simtestmodel1
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kArchitecture:Transformer Cold

The simlamkr1/llama2-simtestmodel1 is a 7 billion parameter Llama 2-based language model. This model was trained using 4-bit quantization with the nf4 quantization type and float16 compute dtype, leveraging PEFT for efficient fine-tuning. It is primarily characterized by its training configuration, which focuses on memory-efficient deployment and fine-tuning.

Loading preview...