101K 7 months ago

Unsloth's DeepSeek-R1 1.58-bit, I just merged the thing and uploaded it here. This is the full 671b model, albeit dynamically quantized to 1.58bits.

f4d24e9138dd · 148B
{
"stop": [
"<|begin▁of▁sentence|>",
"<|end▁of▁sentence|>",
"<|User|>",
"<|Assistant|>"
]
}