8 lines
351 B
Markdown
8 lines
351 B
Markdown
---
|
|
license: mit
|
|
---
|
|
4 bits quantized GGUF weight of phi-3-mini-4k-instruct. Mlx compatible.
|
|
|
|
Official model: https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf (not supported by mlx)
|
|
|
|
Please note that the official phi-3-mini-4k-instruct.gguf model is of llama-2 architecture as stated in the paper (https://huggingface.co/papers/2404.14219) |