| license: apache-2.0 | |
| This is a 2-bit quantized Llama2-7B model using FrameQuant. Use the inference script at https://github.com/vsingh-group/FrameQuant to run the model. |
| license: apache-2.0 | |
| This is a 2-bit quantized Llama2-7B model using FrameQuant. Use the inference script at https://github.com/vsingh-group/FrameQuant to run the model. |