|
|
|
|
|
|
by tgtweak
162 days ago
|
|
|
So basically the quantization in a byteshape model is per-tensor and can be variable and is an "average" in the final result? The results look good - curious why this isn't more prevalent! Would also love to better understand what factors into "accuracy" since there might be some nuance there depending on the measure. |
|
|
It's accuracy across GSM8K, MMLU, IFEVAL and LiveCodeBench.
They detail their methodology here: https://byteshape.com/blogs/Qwen3-4B-I-2507/