metadata
base_model:
- meta-llama/Llama-2-13b-hf
base_model_relation: quantized
license: llama2
Model Card
- Base model:
meta-llama/Llama-2-13b-hf - Quantization method: BlockLDLQ with GuidedQuant Hessian
- Target bit-width: 4
- Backend kernel: QTIP kernel (HYB variant)
- Calibration data: RedPajama (1024 sentences / 4096 tokens)
- Calibration objective: Next-token prediction
- num_groups (for GuidedQuant Hessian): 4
How to run
- Follow the instruction in https://github.com/snu-mllab/GuidedQuant and https://github.com/Cornell-RelaxML/qtip