Remix.run Logo
simonw 6 hours ago

The project doesn't just use 2-bit - that was one of the formats they tried, but when that didn't give good tool calls they switched to 4-bit.

tarruda 4 hours ago | parent [-]

In my case it the 2.46BPW has been working flawless for tool calling, so I don't think 2-bit was the culprit for JSON failing.

They did reduce the number of experts, so maybe that was it?