|
| ▲ | diggan 3 days ago | parent | next [-] |
| As long as it can do tool calling (which it seems to be doing OK with in the first ~30% of the context), the cut off date is less important. Maybe they didn't share it because it's less relevant today? |
| |
| ▲ | baobabKoodaa 3 days ago | parent [-] | | No, I wasn't referring to the cut-off date, I was referring to the fact that this is a fine-tune on top of an older Llama model. All the PR makes it sound like this is a foundational model (pretrained from scratch etc.). |
|
|
| ▲ | fallpeak 3 days ago | parent | prev [-] |
| [dead] |
