any benchmark results?
Thx for sharing the model, although it has impressive generation speed and flappybird results, it would be much better if there are any benchmark results
Thx for sharing the model, although it has impressive generation speed and flappybird results, it would be much better if there are any benchmark results
See here for benchmarks on the test results: https://docs.unsloth.ai/basics/tutorial-how-to-run-deepseek-r1-on-your-own-local-device/deepseek-r1-dynamic-1.58-bit
See here for benchmarks on the test results: https://docs.unsloth.ai/basics/tutorial-how-to-run-deepseek-r1-on-your-own-local-device/deepseek-r1-dynamic-1.58-bit
Those are not benchmark results, that's just a more scientific way of measuring performance on 1 prompt. We want actual benchmarks. Tokens per second speed measured on different hardware would also be nice. By the way, asking a model to make a game that has an endless number of clones on GitHub does not really measure performance, it mainly measures how well the model can recite memorized code, it's not performance, it's just testing memory. I don't mean to be rude, but please don't act like this is sufficient as a benchmark. It just isn't. Please provide actual benchmark results at least, and if possible, also the tokens per second speed on different hardware. And if you do the tokens per second measurements, make sure you say how fast it is for a single user, not just the overall throughput performance. Thanks.