mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-24 02:14:35 +00:00
ad19812cda
* perplexity : faster HellaSwag ggml-ci * perplexity : clean-up ggml-ci * perplexity : no need for decode_helper ggml-ci * perplexity : add comments * perplexity : option to specify max batched tasks via `n_parallel` * perplexity : remove HellaSwag restruction for n_batch |
||
|---|---|---|
| .. | ||
| CMakeLists.txt | ||
| perplexity.cpp | ||
| README.md | ||
perplexity
TODO
Llama 2 70B Scorechart
| Quantization | Model size (GiB) | Perplexity | Delta to fp16 |
|---|---|---|---|
| Q4_0 | 36.20 | 3.5550 | 3.61% |
| Q4_1 | 40.20 | 3.5125 | 2.37% |
| Q5_0 | 44.20 | 3.4744 | 1.26% |
| Q2_K | 27.27 | 3.7339 | 8.82% |
| Q3_K_S | 27.86 | 3.7019 | 7.89% |
| Q3_K_M | 30.83 | 3.5932 | 4.72% |
| Q3_K_L | 33.67 | 3.5617 | 3.80% |
| Q4_K_S | 36.39 | 3.4852 | 1.57% |
| Q4_K_M | 38.54 | 3.4725 | 1.20% |
| Q5_K_S | 44.20 | 3.4483 | 0.50% |
| Q5_K_M | 45.41 | 3.4451 | 0.40% |
| Q6_K | 52.70 | 3.4367 | 0.16% |
| fp16 | 128.5 | 3.4313 | - |