Language Modeling on C4 context length 2048 (test)
8.84PerplexityScaleBITS + RTN
Evaluation results
| Method | Links | |
|---|---|---|
| ScaleBITS + RTNBackbone=Llama2-7B, MP (Mixed-precision)=true, Granularity=block, bits=2.3, Quantizer Type=uniform2026.02 | 8.84 | |
| ICQuantBackbone=Llama2-7B, MP (Mixed-precision)=false, Granularity=element, bits=2.3, Quantizer Type=non-uniform2026.02 | 8.97 | |
| ScaleBITS + RTNBackbone=Llama2-7B, MP (Mixed-precision)=true, Granularity=block, bits=2.1, Quantizer Type=uniform2026.02 | 9.81 | |
| AMQBackbone=Llama2-7B, MP (Mixed-precision)=true, Granularity=layer, bits=2.5, Quantizer Type=uniform2026.02 | 12.37 | |
| SlimLLM+Backbone=Llama2-7B, MP (Mixed-precision)=true, Granularity=channel group, bits=2.1, Quantizer Type=uniform2026.02 | 18.18 | |
| PB-LLMBackbone=Llama2-7B, MP (Mixed-precision)=true, Granularity=element, bits=2.5, Quantizer Type=uniform2026.02 | 32.05 |