Instructions to use g-oQ/embeddinggemma-2-oQ4e with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use g-oQ/embeddinggemma-2-oQ4e with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download g-oQ/embeddinggemma-2-oQ4e --local-dir embeddinggemma-2-oQ4e
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,6 +4,8 @@ tags:
|
|
| 4 |
- mlx
|
| 5 |
- oq
|
| 6 |
- quantized
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
# embeddinggemma-2-oQ4e
|
|
@@ -33,4 +35,4 @@ The effective average is 11.991 bits/weight for the complete checkpoint.
|
|
| 33 |
| Language model | 0.272B | 0.171 GB / 0.160 GiB |
|
| 34 |
| Vision | 0.167B | 0.335 GB / 0.312 GiB |
|
| 35 |
| Audio | 0.305B | 0.610 GB / 0.568 GiB |
|
| 36 |
-
| **Total** | **0.744B** | **1.116 GB / 1.039 GiB** |
|
|
|
|
| 4 |
- mlx
|
| 5 |
- oq
|
| 6 |
- quantized
|
| 7 |
+
base_model:
|
| 8 |
+
- google/embeddinggemma-2
|
| 9 |
---
|
| 10 |
|
| 11 |
# embeddinggemma-2-oQ4e
|
|
|
|
| 35 |
| Language model | 0.272B | 0.171 GB / 0.160 GiB |
|
| 36 |
| Vision | 0.167B | 0.335 GB / 0.312 GiB |
|
| 37 |
| Audio | 0.305B | 0.610 GB / 0.568 GiB |
|
| 38 |
+
| **Total** | **0.744B** | **1.116 GB / 1.039 GiB** |
|