diff options
| author | Georgi Gerganov <ggerganov@gmail.com> | 2023-05-13 09:12:44 +0300 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-05-13 09:12:44 +0300 |
| commit | cdd5350892b1d4e521e930c77341f858fcfcd433 (patch) | |
| tree | 0f090c2c927b7fec50f7e43f7c2e9f80f02f9928 | |
| parent | 738ace394a6f8cf0174e90a97185d9e512c0e200 (diff) | |
readme : update Q4_0 perplexities
I think these were affected by the removal of the `round` during quantization
| -rw-r--r-- | README.md | 6 |
1 files changed, 3 insertions, 3 deletions
@@ -9,7 +9,7 @@ Inference of [LLaMA](https://arxiv.org/abs/2302.13971) model in pure C/C++ **Hot topics:** -- Qauntization formats `Q4` and `Q5` have changed - requantize any old models [(info)](https://github.com/ggerganov/llama.cpp/pull/1405) +- Quantization formats `Q4` and `Q5` have changed - requantize any old models [(info)](https://github.com/ggerganov/llama.cpp/pull/1405) - [Roadmap May 2023](https://github.com/ggerganov/llama.cpp/discussions/1220) <details> @@ -333,12 +333,12 @@ Several quantization methods are supported. They differ in the resulting model d | Model | Measure | F16 | Q4_0 | Q4_1 | Q5_0 | Q5_1 | Q8_0 | |------:|--------------|-------:|-------:|-------:|-------:|-------:|-------:| -| 7B | perplexity | 5.9066 | 6.1620 | 6.0910 | 5.9862 | 5.9481 | 5.9069 | +| 7B | perplexity | 5.9066 | 6.1565 | 6.0910 | 5.9862 | 5.9481 | 5.9069 | | 7B | file size | 13.0G | 4.0G | 4.8G | 4.4G | 4.8G | 7.1G | | 7B | ms/tok @ 4th | 128 | 50 | 54 | 75 | 83 | 75 | | 7B | ms/tok @ 8th | 123 | 44 | 52 | 53 | 58 | 72 | | 7B | bits/weight | 16.0 | 5.0 | 6.0 | 5.5 | 6.0 | 9.0 | -| 13B | perplexity | 5.2543 | 5.3863 | 5.3607 | 5.2856 | 5.2706 | 5.2548 | +| 13B | perplexity | 5.2543 | 5.3860 | 5.3607 | 5.2856 | 5.2706 | 5.2548 | | 13B | file size | 25.0G | 7.6G | 9.1G | 8.4G | 9.1G | 14G | | 13B | ms/tok @ 4th | 239 | 93 | 101 | 150 | 164 | 141 | | 13B | ms/tok @ 8th | 240 | 81 | 96 | 96 | 104 | 136 | |