Instructions to use mlx-community/Lens-3.8B-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/Lens-3.8B-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Lens-3.8B-4bit mlx-community/Lens-3.8B-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
Point code-repo links to canonical xocialize/lens-mlx
Browse files
README.md
CHANGED
|
@@ -23,7 +23,7 @@ denoise trajectory, so quantized samples differ in composition from bf16 but are
|
|
| 23 |
## Usage
|
| 24 |
|
| 25 |
```python
|
| 26 |
-
from lens_mlx.pipeline_mlx import LensPipeline # github.com/xocialize
|
| 27 |
|
| 28 |
# `base` = a microsoft/Lens snapshot providing the tokenizer, GPT-OSS encoder, and FLUX.2 VAE.
|
| 29 |
pipe = LensPipeline.from_pretrained(base, dit_repo="mlx-community/Lens-3.8B-4bit")
|
|
@@ -38,4 +38,4 @@ img.save("out.png")
|
|
| 38 |
- **FLUX.2 VAE:** its own (FLUX.2-dev) terms — **not re-hosted**; fetched from source.
|
| 39 |
|
| 40 |
Upstream: [microsoft/Lens](https://huggingface.co/microsoft/Lens) ·
|
| 41 |
-
MLX port: [xocialize
|
|
|
|
| 23 |
## Usage
|
| 24 |
|
| 25 |
```python
|
| 26 |
+
from lens_mlx.pipeline_mlx import LensPipeline # github.com/xocialize/lens-mlx
|
| 27 |
|
| 28 |
# `base` = a microsoft/Lens snapshot providing the tokenizer, GPT-OSS encoder, and FLUX.2 VAE.
|
| 29 |
pipe = LensPipeline.from_pretrained(base, dit_repo="mlx-community/Lens-3.8B-4bit")
|
|
|
|
| 38 |
- **FLUX.2 VAE:** its own (FLUX.2-dev) terms — **not re-hosted**; fetched from source.
|
| 39 |
|
| 40 |
Upstream: [microsoft/Lens](https://huggingface.co/microsoft/Lens) ·
|
| 41 |
+
MLX port: [xocialize/lens-mlx](https://github.com/xocialize/lens-mlx)
|