| ▲ | stymaar 2 hours ago |
| Flash[1]: 309B total / 15B activated parameters Pro [2]:, 1.02T total / 42B activated parameters [1]: https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL [2]: https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Pro-RL |
|
| ▲ | verdverm 2 hours ago | parent | next [-] |
| There's also a Qwen 3.5 9B distill https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B |
| |
| ▲ | gandreani 2 hours ago | parent [-] | | Those this mean they've fine-tuned this Qwen 3.5 9B on output from the V2.6 model? | | |
|
|
| ▲ | verdverm 2 hours ago | parent | prev | next [-] |
| curious why the HF pill (on the right) always has inaccurate values |
| |
| ▲ | stymaar 2 hours ago | parent [-] | | I noticed the same, and I wonder as well. | | |
| ▲ | verdverm 2 hours ago | parent [-] | | I suspect they are calculating something in the weights or config, I see it pretty consistently with quants |
|
|
|
| ▲ | segmondy an hour ago | parent | prev [-] |
| more like 500B in FP8 |
