mlx-examples
mlx-examples copied to clipboard
Examples in the MLX framework
I’m not finding any working nerf/gaussian-splatting demos on metal. This pair released recently would be amazing to work with and take advantage of the 128gb on the M3. https://github.com/jonbarron/camp_zipnerf
#### Description I ran the following and observed an error 1. Created a new condo env ``` conda create -q -n mlx-examples python=3.8 conda activate mlx-examples ``` 2. Ran pip...
Enhancement request: Implement [RadixAttention](https://arxiv.org/abs/2312.07104) in the KV cache
Could you please add to the documentation what is the way to save models when using MLX - after training is complete final model for inferencing. Perhaps even add sample...
It's mostly just a dump of how we can unlock 10K+ LoRA's on the Hub for MLX-examples. Currently the model example loads the individual weights like here: [code pointer](https://github.com/ml-explore/mlx-examples/blob/b0870ed67976feabc098ffa43a801e0301d335c1/stable_diffusion/stable_diffusion/model_io.py#L19) Majority...
Hi, Any plans to add [Tortoise TTS](https://github.com/neonbjb/tortoise-tts)? Thanks!
This PR adds support for Cohere's Command-R model. Twitter: @Prince_Canuma
Fine-tuning `Qwen/Qwen1.5-0.5B-Chat` reported the following error message: ``` Loading pretrained model Fetching 6 files: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 6/6 [00:00
Could I use the model 't5' when I fine tune with lora.py?
I changed some things that were hard coded before that can be retrieved from `config.json` to enable more models with the `BertForMaskedLM` architecture. I tested it with some other models,...