|
--- |
|
license: llama2 |
|
--- |
|
|
|
Notes only for now, rework needs to be done. |
|
|
|
|
|
Q2_K_S |
|
|
|
Master : |
|
|
|
PR : 2.30 GB (2.73 BPW) 2.14 GiB (2.73 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 7.1215 +/- 0.04057 |
|
|
|
|
|
Q2_K |
|
|
|
Master : |
|
|
|
PR : 2.50 GB (2.97 BPW) 2.33 GiB (2.97 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 6.7865 +/- 0.03827 |
|
|
|
|
|
Q2_K_L |
|
|
|
PR : 2.73 GB (3.25 BPW) 2.55 GiB (3.25 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 6.4599 +/- 0.03643 |
|
|
|
PR 2 : 2.78 GB (3.31 BPW) 2.59 GiB (3.31 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 6.3916 +/- 0.03600 |
|
|
|
|
|
Q3_K_S |
|
|
|
Master : |
|
|
|
PR : 3.00 GB (3.56 BPW) 2.79 GiB (3.56 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 6.1214 +/- 0.03426 |
|
|
|
|
|
Q3_K_M |
|
|
|
Master : |
|
|
|
PR : 3.23 GB (3.84 BPW) 3.01 GiB (3.84 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 6.0295 +/- 0.03371 |
|
|
|
|
|
Q3_K_L |
|
|
|
Master : |
|
|
|
PR : 3.48 GB (4.13 BPW) 3.24 GiB (4.13 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 5.9701 +/- 0.03337 |
|
|
|
|
|
Q3_K_XL |
|
|
|
Master : |
|
|
|
PR : 3.53 GB (4.19 BPW) 3.29 GiB (4.19 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 5.9575 +/- 0.03329 |
|
|
|
PR 2 : 3.52 GB (4.17 BPW) 3.27 GiB (4.17 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 5.9599 +/- 0.03331 |
|
|
|
PR 3 : 3.61 GB (4.29 BPW) 3.36 GiB (4.29 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 5.9399 +/- 0.03320 |
|
|
|
|
|
IQ1_XS |
|
|
|
PR : 1.58 GB (1.87 BPW) 1.47 GiB (1.87 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 13.5558 +/- 0.08231 |
|
|
|
|
|
IQ1_S |
|
|
|
Master : |
|
|
|
PR : 1.63 GB (1.94 BPW) 1.52 GiB (1.94 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 12.2136 +/- 0.07230 |
|
|
|
|
|
IQ1_M |
|
|
|
Master : |
|
|
|
PR : 1.72 GB (2.04 BPW) 1.60 GiB (2.04 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 10.6855 +/- 0.06282 |
|
|
|
|
|
IQ1_XL |
|
|
|
PR : 1.80 GB (2.13 BPW) 1.67 GiB (2.13 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 9.1744 +/- 0.05364 |
|
|
|
PR 2 : 1.81 GB (2.15 BPW) 1.69 GiB (2.15 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 9.0257 +/- 0.05266 |
|
|
|
|
|
IQ2_XXS |
|
|
|
Master : |
|
|
|
PR : 1.93 GB (2.29 BPW) 1.79 GiB (2.29 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 7.9056 +/- 0.04535 |
|
|
|
|
|
IQ2_XS |
|
|
|
Master : |
|
|
|
PR : 2.09 GB (2.48 BPW) 1.94 GiB (2.48 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 7.2907 +/- 0.04164 |
|
|
|
|
|
IQ2_S |
|
|
|
Master : |
|
|
|
PR : 2.18 GB (2.59 BPW) 2.03 GiB (2.59 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 7.0517 +/- 0.04044 |
|
|
|
PR 2 : 2.20 GB (2.61 BPW) 2.05 GiB (2.61 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 7.0115 +/- 0.04014 |
|
|
|
|
|
IQ2_M |
|
|
|
Master : |
|
|
|
PR : 2.37 GB (2.81 BPW) 2.20 GiB (2.81 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 6.5630 +/- 0.03718 |
|
|
|
|
|
IQ2_XL |
|
|
|
PR : 2.50 GB (2.97 BPW) 2.33 GiB (2.97 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 6.4093 +/- 0.03615 |
|
|
|
PR 2 : 2.52 GB (2.99 BPW) 2.35 GiB (2.99 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 6.3800 +/- 0.03599 |
|
|
|
|
|
IQ3_XXS |
|
|
|
Master : |
|
|
|
PR : 2.68 GB (3.19 BPW) 2.50 GiB (3.19 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 6.2120 +/- 0.03494 |
|
|
|
|
|
IQ3_XS |
|
|
|
Master : |
|
|
|
PR : 2.88 GB (3.42 BPW) 2.68 GiB (3.42 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 6.0963 +/- 0.03388 |
|
|
|
PR 2 : 2.89 GB (3.43 BPW) 2.69 GiB (3.43 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 6.0918 +/- 0.03389 |
|
|
|
|
|
IQ3_S |
|
|
|
Master : |
|
|
|
PR : 3.03 GB (3.60 BPW) 2.83 GiB (3.60 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 6.0106 +/- 0.03354 |
|
|
|
|
|
IQ3_M |
|
|
|
Master : |
|
|
|
PR : 3.17 GB (3.77 BPW) 2.96 GiB (3.77 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 5.9766 +/- 0.03370 |
|
|
|
|
|
IQ3_XL |
|
|
|
PR : 3.32 GB (3.94 BPW) 3.09 GiB (3.94 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 5.9523 +/- 0.03345 |
|
|
|
|
|
IQ3_XXL |
|
|
|
PR : 3.40 GB (4.03 BPW) 3.16 GiB (4.03 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 5.9241 +/- 0.03322 |
|
|
|
PR 2 : 3.48 GB (4.13 BPW) 3.24 GiB (4.13 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 5.9076 +/- 0.03308 |
|
|
|
|
|
IQ4_XS |
|
|
|
Master : 3.62 GB (4.30 BPW) 3.37 GiB (4.30 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 5.8784 +/- 0.03286 |
|
|
|
|
|
IQ4_XSR |
|
|
|
PR : 3.97 GB (4.72 BPW) 3.70 GiB (4.72 BPW) |
|
PPL over 655 chunks for n_ctx=512 = 5.8579 +/- 0.03277 |
|
|
|
|
|
FP16 |
|
|
|
Master : |
|
PPL over 655 chunks for n_ctx=512 = 5.7977 +/- 0.03236 |
|
|