Awni Hannun
Awni Hannun
> I'm trying to make things work with T5, I don't have the time to rewrite SpeculativeDecoder for LLM right now (think the goal should still be to change this...
It's a bit more of an art at this point, we've been pushing for some standardization / consistency which is why things look the same. But there are still some...
@mzbac that's a good question. Since different models have slight differences, we are doing a convention now where each model gets a converter. The underlying converters can use HF format...
@sukkritsharmaofficial check the [issue here](https://github.com/ml-explore/mlx/issues/328) for the reason. Looking at that model I think it's possible the issue is the vocab size is not divisible by 32 (I see in...
Agreed, that would be super cool. If anyone is interested in contributing it let us know!
That is strange. Can you share the full stack trace so we can see more precisely the issue arises?
Can you share steps to reproduce?
Closing as we added #461.
Which model are you trying to download and convert? Can you provide a link? In general we don't support arbitrary downloads from HF, but the models in the [MLX community](https://huggingface.co/mlx-community)...
This is cool! We should have something like that. What do you think about integrating it with the main `lora.py` instead as I see there is a lot of code...