mrfakename

Results 198 comments of mrfakename

# Update With [ezgif](https://github.com/phpgif/ezgif), you can easily scan from a directory. ``` composer require phpgif/ezgif ``` ```php use phpgif\EZGif\EZGif; $ez = new EZGif(); $ez->setHeaders(false); $ez->generateFromDir('imgs'); $ez->displayGif(); ``` # Original Answer...

If the gguf PR is merged, then MLX -> GGUF -> reverse the GGUF convert.py script to create HF model? The convert.py script seems in llama.cpp seems quite complicated, but...

Ah, nice - before I was trying to convert it with the [Phi script](https://github.com/ml-explore/mlx-examples/blob/main/phi2/convert.py) :). So does LoRA w/ MLX supports TinyLlama?

Hi, Thank you so much! Is there a timeline for adding LoRA support for TinyLlama, now that the 3T version is released? Thank you!

Thanks! Also is there a way to convert MLX -> HF?

cc @LinB203

Personally, I do think open access is better than closed-source with no way for the public to use it but it would be nice to not label it as open...

Thanks!!