Results for Optimizing OPT Model seems unusually high for 4 bits per tensor

[amitrana001]

Looking at the data for 4 bits per tensor in the results table for optimizing OPT model, the values for c4 Perplexity and wikitext2 Perplexity seem unusually high compared to the other configurations.
Are these values correct or there is some typo?

Code link here:

coremltools/docs-guides/source/opt-opt1_3.md

Line 74 in c3ea4cf

| 4 bits per tensor | 0.66 | 18763 | 31087 | 21.66 |

[junpeiz]

My understanding is that the 4-bit per-tensor hurts that model too much, so the perplexity exploded. By using more fine-grained quantization (per-channel, per-block), the perplexity gets back to normal.
(cc @aseemw to confirm it's not a typo)