Instructions to use mlx-community/Lens-3.8B-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/Lens-3.8B-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Lens-3.8B-8bit mlx-community/Lens-3.8B-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
Reserve name; weights coming soon
Browse files
README.md
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: mlx
|
| 4 |
+
pipeline_tag: text-to-image
|
| 5 |
+
tags: [mlx, text-to-image, diffusion, lens, apple-silicon]
|
| 6 |
+
base_model: microsoft/Lens
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# Lens-3.8B-8bit (MLX) — coming soon
|
| 10 |
+
|
| 11 |
+
`int8`/8bit MLX conversion of the [microsoft/Lens](https://huggingface.co/microsoft/Lens) 3.8B
|
| 12 |
+
text-to-image DiT for Apple Silicon (~4.36 GB). Weights upload imminent.
|
| 13 |
+
|
| 14 |
+
Full-precision release: [mlx-community/Lens-3.8B-bf16](https://huggingface.co/mlx-community/Lens-3.8B-bf16).
|
| 15 |
+
Code: [xocialize-code/lens-mlx](https://github.com/xocialize-code/lens-mlx).
|